Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 757 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.4461. Min Act: -0.1700
Data Index: 3065074 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.3523. Min Act: -0.1700
Data Index: 7224881 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.3523. Min Act: -0.1700
Data Index: 3466311 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2898. Min Act: -0.1700
Data Index: 600648 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2586. Min Act: -0.1700
Data Index: 8053113 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2586. Min Act: -0.1700
Data Index: 5369306 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2273. Min Act: -0.1700
Data Index: 7772326 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2273. Min Act: -0.1700
Data Index: 1069651 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2273. Min Act: -0.1700
Data Index: 7550488 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1961. Min Act: -0.1700
Data Index: 6337576 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.2273. Min Act: -0.1700
Data Index: 5305075 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1648. Min Act: -0.1700
Data Index: 7703610 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1648. Min Act: -0.1700
Data Index: 5947426 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1648. Min Act: -0.1700
Data Index: 2575030 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1648. Min Act: -0.1700
Data Index: 261787 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1648. Min Act: -0.1700
Data Index: 466060 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1336. Min Act: -0.1700
Data Index: 602556 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1336. Min Act: -0.1700
Data Index: 696154 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1023. Min Act: -0.1700
Data Index: 4437805 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4461. Min Range: -6.4461
Max Act: 6.1648. Min Act: -0.1700
Data Index: 3700494 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19