Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2379 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.3739. Min Act: -0.1699
Data Index: 1419001 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.3114. Min Act: -0.1700
Data Index: 7366519 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.2489. Min Act: -0.1700
Data Index: 314473 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.2802. Min Act: -0.1700
Data Index: 4451721 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.2177. Min Act: -0.1700
Data Index: 6800823 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.2489. Min Act: -0.1700
Data Index: 642849 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3793521 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.2177. Min Act: -0.1700
Data Index: 3493398 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.2489. Min Act: -0.1700
Data Index: 3791995 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1864. Min Act: -0.1700
Data Index: 3785771 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1864. Min Act: -0.1700
Data Index: 1526169 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1552. Min Act: -0.1700
Data Index: 7979675 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1239. Min Act: -0.1700
Data Index: 7160134 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1239. Min Act: -0.1700
Data Index: 2329108 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1239. Min Act: -0.1700
Data Index: 7813211 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3791996 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.1239. Min Act: -0.1700
Data Index: 5537992 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.0614. Min Act: -0.1700
Data Index: 3582900 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.0927. Min Act: -0.1700
Data Index: 3015966 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3739. Min Range: -5.3739
Max Act: 5.0302. Min Act: -0.1700
Data Index: 2225362 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19