Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.5672. Min Act: -0.1700
Data Index: 2305315 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.5046. Min Act: -0.1700
Data Index: 3400494 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.5046. Min Act: -0.1700
Data Index: 4992952 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4733. Min Act: -0.1700
Data Index: 1676216 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4733. Min Act: -0.1700
Data Index: 1917969 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4733. Min Act: -0.1700
Data Index: 5159411 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4419. Min Act: -0.1700
Data Index: 897668 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4419. Min Act: -0.1700
Data Index: 8676502 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4419. Min Act: -0.1700
Data Index: 7670173 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4106. Min Act: -0.1700
Data Index: 4683534 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4106. Min Act: -0.1700
Data Index: 6501926 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4106. Min Act: -0.1700
Data Index: 7510974 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.4419. Min Act: -0.1700
Data Index: 1819600 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 5245657 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 1191623 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 2169467 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 2664339 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 284957 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 4562995 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5672. Min Range: -3.5672
Max Act: 3.3792. Min Act: -0.1700
Data Index: 3620631 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19