Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.9124. Min Act: -0.1700
Data Index: 2955577 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.8811. Min Act: -0.1700
Data Index: 2276052 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.7560. Min Act: -0.1700
Data Index: 2474821 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.7404. Min Act: -0.1700
Data Index: 6788204 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.7091. Min Act: -0.1700
Data Index: 1853069 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5996. Min Act: -0.1700
Data Index: 2218911 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5996. Min Act: -0.1700
Data Index: 1018275 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5996. Min Act: -0.1700
Data Index: 1476978 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 97031 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 971387 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 876998 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 481141 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 771833 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 1418806 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 468044 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 630029 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 277480 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 144644 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 72460 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9124. Min Range: -3.9124
Max Act: 3.5683. Min Act: -0.1700
Data Index: 1166411 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19