Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3518 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0527. Min Range: -5.0527
Max Act: 5.0527. Min Act: -0.1700
Data Index: 6713755 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.7714. Min Act: -0.1700
Data Index: 3159112 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.4589. Min Act: -0.1700
Data Index: 4185902 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.4589. Min Act: -0.1700
Data Index: 6899026 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.4589. Min Act: -0.1700
Data Index: 4331634 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3964. Min Act: -0.1700
Data Index: 2231341 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.4277. Min Act: -0.1700
Data Index: 7761217 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.4277. Min Act: -0.1700
Data Index: 3143614 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.4277. Min Act: -0.1700
Data Index: 1670045 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3964. Min Act: -0.1700
Data Index: 7761218 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3964. Min Act: -0.1700
Data Index: 8056861 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3964. Min Act: -0.1700
Data Index: 650649 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3964. Min Act: -0.1700
Data Index: 6042152 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 5234420 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 3153364 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 1722902 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 702648 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 2226292 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 4893222 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0527. Min Range: -5.0527
Max Act: 4.3652. Min Act: -0.1700
Data Index: 8150827 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19