Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.8547. Min Act: -0.1700
Data Index: 8483205 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.7910. Min Act: -0.1700
Data Index: 8291627 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.7910. Min Act: -0.1700
Data Index: 3538367 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.7432. Min Act: -0.1700
Data Index: 555407 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.7272. Min Act: -0.1700
Data Index: 3476371 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6952. Min Act: -0.1700
Data Index: 4590594 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6952. Min Act: -0.1700
Data Index: 4124551 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6792. Min Act: -0.1700
Data Index: 3019701 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6632. Min Act: -0.1700
Data Index: 2214326 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6632. Min Act: -0.1700
Data Index: 4083308 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6632. Min Act: -0.1700
Data Index: 6699959 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6792. Min Act: -0.1700
Data Index: 1987193 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6632. Min Act: -0.1700
Data Index: 8016431 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6471. Min Act: -0.1700
Data Index: 6766890 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6632. Min Act: -0.1700
Data Index: 634351 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6471. Min Act: -0.1700
Data Index: 2273573 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6311. Min Act: -0.1700
Data Index: 1093765 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6311. Min Act: -0.1700
Data Index: 6278529 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6311. Min Act: -0.1700
Data Index: 4112996 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8547. Min Range: -2.8547
Max Act: 2.6311. Min Act: -0.1700
Data Index: 7972893 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19