Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.6198. Min Act: -0.1700
Data Index: 6220369 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.5573. Min Act: -0.1700
Data Index: 2012215 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4948. Min Act: -0.1700
Data Index: 2355321 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4635. Min Act: -0.1700
Data Index: 3759876 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4323. Min Act: -0.1700
Data Index: 1191592 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4010. Min Act: -0.1700
Data Index: 582505 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4323. Min Act: -0.1700
Data Index: 2488100 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 3298026 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4010. Min Act: -0.1700
Data Index: 3184138 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4010. Min Act: -0.1700
Data Index: 6988777 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4010. Min Act: -0.1700
Data Index: 3101504 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 1098722 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3385. Min Act: -0.1700
Data Index: 3729200 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 1151025 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 7333630 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4010. Min Act: -0.1700
Data Index: 864155 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 5778850 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.4323. Min Act: -0.1700
Data Index: 4509864 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 5559240 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6198. Min Range: -4.6198
Max Act: 4.3698. Min Act: -0.1700
Data Index: 5537264 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19