Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2125 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6358. Min Range: -10.6358
Max Act: 10.6358. Min Act: -0.1700
Data Index: 1514586 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6358. Min Range: -10.6358
Max Act: 10.5733. Min Act: -0.1700
Data Index: 5536206 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6358. Min Range: -10.6358
Max Act: 10.1983. Min Act: -0.1700
Data Index: 135087 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6358. Min Range: -10.6358
Max Act: 10.1358. Min Act: -0.1700
Data Index: 5048422 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6358. Min Range: -10.6358
Max Act: 10.0108. Min Act: -0.1700
Data Index: 2925407 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.9483. Min Act: -0.1700
Data Index: 1834487 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.9483. Min Act: -0.1700
Data Index: 6194532 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.8858. Min Act: -0.1700
Data Index: 3573081 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.8858. Min Act: -0.1700
Data Index: 3449709 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.8233. Min Act: -0.1700
Data Index: 2377864 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.7608. Min Act: -0.1700
Data Index: 1373765 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6983. Min Act: -0.1700
Data Index: 8490469 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.7608. Min Act: -0.1700
Data Index: 280938 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6983. Min Act: -0.1700
Data Index: 1675377 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6983. Min Act: -0.1700
Data Index: 5691975 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6983. Min Act: -0.1700
Data Index: 288613 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6358. Min Act: -0.1700
Data Index: 1219915 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6358. Min Act: -0.1700
Data Index: 5586233 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6358. Min Act: -0.1700
Data Index: 3875424 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6358. Min Range: -10.6358
Max Act: 9.6358. Min Act: -0.1700
Data Index: 6453790 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19