Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5018 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.5573. Min Act: -0.1700
Data Index: 1120957 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.4948. Min Act: -0.1700
Data Index: 1030546 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.4323. Min Act: -0.1700
Data Index: 3327457 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.4323. Min Act: -0.1700
Data Index: 4172 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.3698. Min Act: -0.1700
Data Index: 240975 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.3386. Min Act: -0.1700
Data Index: 2069656 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2761. Min Act: -0.1700
Data Index: 2117656 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.3073. Min Act: -0.1700
Data Index: 1268360 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2761. Min Act: -0.1700
Data Index: 7089150 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2761. Min Act: -0.1700
Data Index: 5827723 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2448. Min Act: -0.1700
Data Index: 7014831 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2448. Min Act: -0.1700
Data Index: 1262119 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2136. Min Act: -0.1700
Data Index: 6469971 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2448. Min Act: -0.1700
Data Index: 8031747 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.1823. Min Act: -0.1700
Data Index: 7580071 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.1823. Min Act: -0.1700
Data Index: 5045522 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.1823. Min Act: -0.1700
Data Index: 2917049 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.2136. Min Act: -0.1700
Data Index: 4879624 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.1823. Min Act: -0.1700
Data Index: 5309560 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5573. Min Range: -6.5573
Max Act: 6.1823. Min Act: -0.1700
Data Index: 687572 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19