Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3537 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0741. Min Range: -5.0741
Max Act: 5.0741. Min Act: -0.1700
Data Index: 2347183 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0741. Min Range: -5.0741
Max Act: 5.0429. Min Act: -0.1700
Data Index: 6174344 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.9179. Min Act: -0.1700
Data Index: 8298353 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.9491. Min Act: -0.1700
Data Index: 5703155 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.9179. Min Act: -0.1700
Data Index: 7734392 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8554. Min Act: -0.1700
Data Index: 8198787 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7929. Min Act: -0.1700
Data Index: 552766 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7304. Min Act: -0.1700
Data Index: 5478317 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6679. Min Act: -0.1700
Data Index: 741962 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6679. Min Act: -0.1700
Data Index: 4434981 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6679. Min Act: -0.1700
Data Index: 857393 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6679. Min Act: -0.1700
Data Index: 1374269 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6054. Min Act: -0.1700
Data Index: 1833690 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.5741. Min Act: -0.1700
Data Index: 6570197 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6054. Min Act: -0.1700
Data Index: 8013836 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6054. Min Act: -0.1700
Data Index: 297643 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6054. Min Act: -0.1700
Data Index: 5764998 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.6054. Min Act: -0.1700
Data Index: 996345 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.5741. Min Act: -0.1700
Data Index: 3113540 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.5741. Min Act: -0.1700
Data Index: 5372254 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19