Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1699. Min Range: -8.1699
Max Act: 8.1699. Min Act: -0.1700
Data Index: 4815057 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.9824. Min Act: -0.1700
Data Index: 6489812 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.7324. Min Act: -0.1700
Data Index: 2700890 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.6699. Min Act: -0.1700
Data Index: 4132830 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.6699. Min Act: -0.1700
Data Index: 4457720 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.6699. Min Act: -0.1700
Data Index: 4091906 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.6699. Min Act: -0.1700
Data Index: 3463759 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.5449. Min Act: -0.1700
Data Index: 8578358 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.5449. Min Act: -0.1700
Data Index: 8102191 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.5137. Min Act: -0.1700
Data Index: 7124682 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.4824. Min Act: -0.1700
Data Index: 7562477 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.4512. Min Act: -0.1700
Data Index: 1248962 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.4199. Min Act: -0.1700
Data Index: 1962074 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.4199. Min Act: -0.1700
Data Index: 1358070 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.4199. Min Act: -0.1700
Data Index: 6559600 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.3887. Min Act: -0.1700
Data Index: 2277793 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.3574. Min Act: -0.1700
Data Index: 3743036 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.3887. Min Act: -0.1700
Data Index: 7200136 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.3262. Min Act: -0.1700
Data Index: 7758226 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1699. Min Range: -8.1699
Max Act: 7.2949. Min Act: -0.1700
Data Index: 7176716 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19