Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6670998 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.1325. Min Act: -0.1700
Data Index: 3318505 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.1325. Min Act: -0.1700
Data Index: 2081878 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6238398 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0700. Min Act: -0.1700
Data Index: 7976748 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0387. Min Act: -0.1700
Data Index: 235085 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0700. Min Act: -0.1700
Data Index: 6670999 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0387. Min Act: -0.1700
Data Index: 1601668 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0387. Min Act: -0.1700
Data Index: 7254173 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0074. Min Act: -0.1700
Data Index: 8578320 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0074. Min Act: -0.1700
Data Index: 8587777 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0074. Min Act: -0.1700
Data Index: 4908386 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1325. Min Range: -4.1325
Max Act: 4.0074. Min Act: -0.1700
Data Index: 3559784 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 7509162 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 4293656 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 576105 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 2008887 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 906494 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 432712 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1325. Min Range: -4.1325
Max Act: 3.9762. Min Act: -0.1700
Data Index: 6589885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19