Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6362 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.7152. Min Act: -0.1700
Data Index: 118641 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.6214. Min Act: -0.1700
Data Index: 3487089 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.5589. Min Act: -0.1700
Data Index: 8805974 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.4652. Min Act: -0.1700
Data Index: 5931442 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.4027. Min Act: -0.1700
Data Index: 3656277 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.3402. Min Act: -0.1700
Data Index: 8572247 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.3714. Min Act: -0.1700
Data Index: 2499728 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.3089. Min Act: -0.1700
Data Index: 8287644 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.2777. Min Act: -0.1700
Data Index: 2375876 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.2152. Min Act: -0.1700
Data Index: 3716116 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1839. Min Act: -0.1700
Data Index: 6319234 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1527. Min Act: -0.1700
Data Index: 797155 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1527. Min Act: -0.1700
Data Index: 4607148 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1527. Min Act: -0.1700
Data Index: 7226696 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1527. Min Act: -0.1700
Data Index: 7979665 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1672421 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1527. Min Act: -0.1700
Data Index: 356932 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1214. Min Act: -0.1700
Data Index: 3676317 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.0902. Min Act: -0.1700
Data Index: 3534526 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7152. Min Range: -6.7152
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6058744 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19