Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4429. Min Range: -7.4429
Max Act: 7.4429. Min Act: -0.1700
Data Index: 1765674 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4429. Min Range: -7.4429
Max Act: 7.2866. Min Act: -0.1700
Data Index: 1258961 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4429. Min Range: -7.4429
Max Act: 7.2241. Min Act: -0.1700
Data Index: 5547050 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4429. Min Range: -7.4429
Max Act: 7.0991. Min Act: -0.1700
Data Index: 549687 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.9741. Min Act: -0.1700
Data Index: 7562090 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.9116. Min Act: -0.1700
Data Index: 5487021 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.9116. Min Act: -0.1700
Data Index: 881504 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8804. Min Act: -0.1700
Data Index: 16730 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8491. Min Act: -0.1700
Data Index: 2483024 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8491. Min Act: -0.1700
Data Index: 1791374 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8179. Min Act: -0.1700
Data Index: 2931374 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8491. Min Act: -0.1700
Data Index: 2811701 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8179. Min Act: -0.1700
Data Index: 5145225 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.8179. Min Act: -0.1700
Data Index: 1138561 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.7866. Min Act: -0.1700
Data Index: 1765675 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.7554. Min Act: -0.1700
Data Index: 3198143 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.7554. Min Act: -0.1700
Data Index: 2493803 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.7554. Min Act: -0.1700
Data Index: 6381186 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.7241. Min Act: -0.1700
Data Index: 2344860 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4429. Min Range: -7.4429
Max Act: 6.7241. Min Act: -0.1700
Data Index: 859811 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19