Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 571 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.8086. Min Act: -0.1700
Data Index: 3139725 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.7774. Min Act: -0.1700
Data Index: 4403132 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.7774. Min Act: -0.1700
Data Index: 3736654 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.7149. Min Act: -0.1700
Data Index: 5317472 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.6524. Min Act: -0.1700
Data Index: 6594484 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.6211. Min Act: -0.1700
Data Index: 8488137 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.5586. Min Act: -0.1700
Data Index: 6327775 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4649. Min Act: -0.1700
Data Index: 4957383 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.5274. Min Act: -0.1700
Data Index: 862369 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.5586. Min Act: -0.1700
Data Index: 4997066 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4336. Min Act: -0.1700
Data Index: 5371028 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4961. Min Act: -0.1700
Data Index: 7336558 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4961. Min Act: -0.1700
Data Index: 7081712 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4649. Min Act: -0.1700
Data Index: 8092900 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4649. Min Act: -0.1700
Data Index: 208659 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4649. Min Act: -0.1700
Data Index: 7233358 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4336. Min Act: -0.1700
Data Index: 6729379 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4024. Min Act: -0.1700
Data Index: 2388048 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4336. Min Act: -0.1700
Data Index: 4632148 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8086. Min Range: -4.8086
Max Act: 4.4961. Min Act: -0.1700
Data Index: 5862625 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19