Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.8622. Min Act: -0.1700
Data Index: 1992531 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.7997. Min Act: -0.1700
Data Index: 5440950 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.7997. Min Act: -0.1700
Data Index: 8819676 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.7997. Min Act: -0.1700
Data Index: 8378838 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.7372. Min Act: -0.1700
Data Index: 6479118 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.6122. Min Act: -0.1700
Data Index: 5777085 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.6122. Min Act: -0.1700
Data Index: 6943375 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.6435. Min Act: -0.1700
Data Index: 3305586 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5497. Min Act: -0.1700
Data Index: 1678176 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5497. Min Act: -0.1700
Data Index: 107918 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5185. Min Act: -0.1700
Data Index: 3300782 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5185. Min Act: -0.1700
Data Index: 5268135 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5185. Min Act: -0.1700
Data Index: 2443185 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5497. Min Act: -0.1700
Data Index: 7730812 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.5185. Min Act: -0.1700
Data Index: 4593686 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.4560. Min Act: -0.1700
Data Index: 3172505 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.4872. Min Act: -0.1700
Data Index: 8462355 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.4560. Min Act: -0.1700
Data Index: 7924002 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.4560. Min Act: -0.1700
Data Index: 162689 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8622. Min Range: -7.8622
Max Act: 7.4560. Min Act: -0.1700
Data Index: 106901 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19