Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6357 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4512618 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 5372929 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9574. Min Act: -0.1700
Data Index: 2121192 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4122292 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9574. Min Act: -0.1700
Data Index: 4899196 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9574. Min Act: -0.1700
Data Index: 3456429 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9574. Min Act: -0.1700
Data Index: 633624 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9574. Min Act: -0.1700
Data Index: 5801125 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9574. Min Act: -0.1700
Data Index: 294218 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 7715328 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 4293581 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 7074469 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 6788714 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 1979535 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 1121306 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 6404470 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.8949. Min Act: -0.1700
Data Index: 6403046 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 5952058 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 5775754 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9886. Min Range: -5.9886
Max Act: 5.9261. Min Act: -0.1700
Data Index: 5761718 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19