Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.7414. Min Act: -0.1700
Data Index: 211382 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.6789. Min Act: -0.1700
Data Index: 3082823 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.6164. Min Act: -0.1700
Data Index: 5415128 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.5852. Min Act: -0.1700
Data Index: 108349 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.5227. Min Act: -0.1700
Data Index: 5942442 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.5539. Min Act: -0.1700
Data Index: 5848474 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.5227. Min Act: -0.1700
Data Index: 2878564 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4914. Min Act: -0.1700
Data Index: 4967936 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4914. Min Act: -0.1700
Data Index: 5239330 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.5227. Min Act: -0.1700
Data Index: 862316 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4914. Min Act: -0.1700
Data Index: 5175527 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4602. Min Act: -0.1700
Data Index: 7733645 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4602. Min Act: -0.1700
Data Index: 1405630 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4602. Min Act: -0.1700
Data Index: 880306 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4602. Min Act: -0.1700
Data Index: 879399 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4289. Min Act: -0.1700
Data Index: 5370591 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4289. Min Act: -0.1700
Data Index: 4424396 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4289. Min Act: -0.1700
Data Index: 382967 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4289. Min Act: -0.1700
Data Index: 5631135 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7414. Min Range: -5.7414
Max Act: 5.4289. Min Act: -0.1700
Data Index: 5992890 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19