Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3140 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0715. Min Range: -9.0715
Max Act: 9.0715. Min Act: -0.1700
Data Index: 5955518 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0715. Min Range: -9.0715
Max Act: 9.0715. Min Act: -0.1700
Data Index: 5759342 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.8215. Min Act: -0.1700
Data Index: 6014421 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.6340. Min Act: -0.1700
Data Index: 5351828 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.5715. Min Act: -0.1700
Data Index: 8063532 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.5715. Min Act: -0.1700
Data Index: 764239 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.5090. Min Act: -0.1700
Data Index: 3987989 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.5090. Min Act: -0.1700
Data Index: 5184876 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.5090. Min Act: -0.1700
Data Index: 2530250 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.4465. Min Act: -0.1700
Data Index: 3456287 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3840. Min Act: -0.1700
Data Index: 5166598 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3840. Min Act: -0.1700
Data Index: 5394074 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3840. Min Act: -0.1700
Data Index: 7503629 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3840. Min Act: -0.1700
Data Index: 6876040 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3215. Min Act: -0.1700
Data Index: 7967891 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3215. Min Act: -0.1700
Data Index: 821185 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3215. Min Act: -0.1700
Data Index: 2820068 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3215. Min Act: -0.1700
Data Index: 709884 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3215. Min Act: -0.1700
Data Index: 4908213 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0715. Min Range: -9.0715
Max Act: 8.3215. Min Act: -0.1700
Data Index: 2994328 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19