Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8870. Min Range: -11.8870
Max Act: 11.8870. Min Act: -0.1700
Data Index: 8657577 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8870. Min Range: -11.8870
Max Act: 11.4495. Min Act: -0.1700
Data Index: 6777019 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8870. Min Range: -11.8870
Max Act: 11.3870. Min Act: -0.1700
Data Index: 7411869 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.8870. Min Act: -0.1700
Data Index: 1786768 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.8245. Min Act: -0.1700
Data Index: 444957 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.7620. Min Act: -0.1700
Data Index: 2269648 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.7620. Min Act: -0.1700
Data Index: 8445597 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.6995. Min Act: -0.1700
Data Index: 3835761 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.6995. Min Act: -0.1700
Data Index: 2278715 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.6370. Min Act: -0.1700
Data Index: 218725 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.5745. Min Act: -0.1700
Data Index: 8374991 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.5745. Min Act: -0.1700
Data Index: 6353985 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.5120. Min Act: -0.1700
Data Index: 4742311 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.5120. Min Act: -0.1700
Data Index: 4003562 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.3870. Min Act: -0.1700
Data Index: 8733638 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.4495. Min Act: -0.1700
Data Index: 8831135 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.3870. Min Act: -0.1700
Data Index: 5367225 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.4495. Min Act: -0.1700
Data Index: 8214454 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.4495. Min Act: -0.1700
Data Index: 4320912 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8870. Min Range: -11.8870
Max Act: 10.3870. Min Act: -0.1700
Data Index: 8561693 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19