Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.7174. Min Act: -0.1700
Data Index: 1235554 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.5924. Min Act: -0.1700
Data Index: 7988845 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4361. Min Act: -0.1700
Data Index: 7750338 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3736. Min Act: -0.1700
Data Index: 4516748 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.4049. Min Act: -0.1700
Data Index: 2877744 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 7957226 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 2215271 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3424. Min Act: -0.1700
Data Index: 3421764 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3111. Min Act: -0.1700
Data Index: 5945281 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3111. Min Act: -0.1700
Data Index: 5296685 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3111. Min Act: -0.1700
Data Index: 7923192 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3111. Min Act: -0.1700
Data Index: 8364444 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.3111. Min Act: -0.1700
Data Index: 6799582 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2799. Min Act: -0.1700
Data Index: 500556 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2486. Min Act: -0.1700
Data Index: 290176 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.2799. Min Act: -0.1700
Data Index: 7856851 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.1861. Min Act: -0.1700
Data Index: 8149072 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.1861. Min Act: -0.1700
Data Index: 1104095 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.1861. Min Act: -0.1700
Data Index: 2299571 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7174. Min Range: -6.7174
Max Act: 6.1549. Min Act: -0.1700
Data Index: 5237887 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19