Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.2150. Min Act: -0.1700
Data Index: 436416 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1993. Min Act: -0.1700
Data Index: 1406973 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1993. Min Act: -0.1700
Data Index: 6805125 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1836. Min Act: -0.1700
Data Index: 1335338 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1836. Min Act: -0.1700
Data Index: 6265586 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1836. Min Act: -0.1700
Data Index: 1406968 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1678. Min Act: -0.1700
Data Index: 5724987 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1678. Min Act: -0.1700
Data Index: 5297690 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1678. Min Act: -0.1700
Data Index: 7544562 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1678. Min Act: -0.1700
Data Index: 3193848 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1521. Min Act: -0.1700
Data Index: 2546879 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1521. Min Act: -0.1700
Data Index: 734621 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1521. Min Act: -0.1700
Data Index: 2571900 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1521. Min Act: -0.1700
Data Index: 3342233 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1521. Min Act: -0.1700
Data Index: 7544563 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1364. Min Act: -0.1700
Data Index: 6632599 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1364. Min Act: -0.1700
Data Index: 7801618 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1364. Min Act: -0.1700
Data Index: 1673089 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1364. Min Act: -0.1700
Data Index: 4399360 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1364. Min Act: -0.1698
Data Index: 1406967 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19