Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4498. Min Range: -7.4498
Max Act: 7.4498. Min Act: -0.1700
Data Index: 7124874 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4498. Min Range: -7.4498
Max Act: 7.2623. Min Act: -0.1700
Data Index: 4903803 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4498. Min Range: -7.4498
Max Act: 7.0123. Min Act: -0.1700
Data Index: 8251547 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.9186. Min Act: -0.1700
Data Index: 1647968 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.8561. Min Act: -0.1700
Data Index: 5813360 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.8561. Min Act: -0.1700
Data Index: 2615622 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7936. Min Act: -0.1700
Data Index: 8322998 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7936. Min Act: -0.1700
Data Index: 2153069 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7936. Min Act: -0.1700
Data Index: 7523960 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7623. Min Act: -0.1700
Data Index: 6532098 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7311. Min Act: -0.1700
Data Index: 1155948 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7311. Min Act: -0.1700
Data Index: 5456060 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7311. Min Act: -0.1700
Data Index: 8653132 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7311. Min Act: -0.1700
Data Index: 4601965 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.7311. Min Act: -0.1700
Data Index: 6041817 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.6686. Min Act: -0.1700
Data Index: 3174853 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.6998. Min Act: -0.1700
Data Index: 7198463 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.6686. Min Act: -0.1700
Data Index: 2404489 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.6998. Min Act: -0.1700
Data Index: 4023026 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4498. Min Range: -7.4498
Max Act: 6.6686. Min Act: -0.1700
Data Index: 5694187 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19