Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5768 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.7369. Min Act: -0.1700
Data Index: 2888964 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.3932. Min Act: -0.1700
Data Index: 8605626 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.4244. Min Act: -0.1700
Data Index: 5391002 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.3932. Min Act: -0.1700
Data Index: 5258696 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1744. Min Act: -0.1700
Data Index: 6026026 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1744. Min Act: -0.1700
Data Index: 794559 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1432. Min Act: -0.1700
Data Index: 5582672 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1432. Min Act: -0.1700
Data Index: 6897709 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1119. Min Act: -0.1700
Data Index: 6800478 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1119. Min Act: -0.1700
Data Index: 7352459 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.1119. Min Act: -0.1700
Data Index: 2969381 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0807. Min Act: -0.1700
Data Index: 6795374 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0807. Min Act: -0.1700
Data Index: 7052690 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0494. Min Act: -0.1700
Data Index: 4404978 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0182. Min Act: -0.1700
Data Index: 644802 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4088848 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0182. Min Act: -0.1700
Data Index: 4694841 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7369. Min Range: -5.7369
Max Act: 5.0182. Min Act: -0.1700
Data Index: 2237611 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7369. Min Range: -5.7369
Max Act: 4.9869. Min Act: -0.1700
Data Index: 4264944 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7369. Min Range: -5.7369
Max Act: 4.9869. Min Act: -0.1700
Data Index: 4819621 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19