Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.6370. Min Act: -0.1700
Data Index: 1146741 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.4495. Min Act: -0.1700
Data Index: 4992882 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.2933. Min Act: -0.1700
Data Index: 3714462 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.2308. Min Act: -0.1700
Data Index: 2500837 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.1995. Min Act: -0.1700
Data Index: 481077 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.1995. Min Act: -0.1699
Data Index: 7607038 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.1370. Min Act: -0.1700
Data Index: 561712 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.0745. Min Act: -0.1700
Data Index: 3723205 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.0120. Min Act: -0.1700
Data Index: 7032980 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6370. Min Range: -5.6370
Max Act: 5.0120. Min Act: -0.1700
Data Index: 6969783 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9808. Min Act: -0.1700
Data Index: 2856730 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9808. Min Act: -0.1700
Data Index: 947638 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9495. Min Act: -0.1700
Data Index: 5934251 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9495. Min Act: -0.1700
Data Index: 4255074 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9495. Min Act: -0.1700
Data Index: 7162313 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9495. Min Act: -0.1700
Data Index: 2368351 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9183. Min Act: -0.1700
Data Index: 7805210 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9495. Min Act: -0.1700
Data Index: 6272780 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9183. Min Act: -0.1700
Data Index: 1828684 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6370. Min Range: -5.6370
Max Act: 4.9183. Min Act: -0.1700
Data Index: 2486316 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19