Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4479 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4929. Min Act: -0.1700
Data Index: 650853 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4304. Min Act: -0.1700
Data Index: 8652775 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.4304. Min Act: -0.1700
Data Index: 4161187 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3991. Min Act: -0.1700
Data Index: 6594841 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3679. Min Act: -0.1700
Data Index: 2480404 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3054. Min Act: -0.1700
Data Index: 1599715 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3054. Min Act: -0.1700
Data Index: 4009798 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3054. Min Act: -0.1700
Data Index: 3495342 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.3054. Min Act: -0.1700
Data Index: 5656416 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 7719402 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 3131868 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2116. Min Act: -0.1700
Data Index: 2650238 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 4069586 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2116. Min Act: -0.1700
Data Index: 4935474 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2116. Min Act: -0.1700
Data Index: 4879648 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.2429. Min Act: -0.1700
Data Index: 3803658 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.1804. Min Act: -0.1700
Data Index: 3170580 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.1804. Min Act: -0.1700
Data Index: 5008378 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.1804. Min Act: -0.1700
Data Index: 2025691 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4929. Min Range: -6.4929
Max Act: 6.1804. Min Act: -0.1700
Data Index: 1211050 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19