Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4664 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.9627. Min Act: -0.1700
Data Index: 1952402 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.7440. Min Act: -0.1700
Data Index: 3511530 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.7127. Min Act: -0.1700
Data Index: 4016937 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.7127. Min Act: -0.1700
Data Index: 1695600 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.6502. Min Act: -0.1700
Data Index: 7311859 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.4627. Min Act: -0.1700
Data Index: 8742216 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.4627. Min Act: -0.1700
Data Index: 6346998 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.4002. Min Act: -0.1700
Data Index: 1003235 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.4002. Min Act: -0.1700
Data Index: 4918014 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.2752. Min Act: -0.1700
Data Index: 6347003 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.2440. Min Act: -0.1700
Data Index: 6242320 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.2127. Min Act: -0.1700
Data Index: 3945579 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.1815. Min Act: -0.1700
Data Index: 1680285 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.1190. Min Act: -0.1700
Data Index: 5646430 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.0877. Min Act: -0.1700
Data Index: 4568616 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.0565. Min Act: -0.1700
Data Index: 6193341 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.0565. Min Act: -0.1700
Data Index: 8615229 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.0252. Min Act: -0.1700
Data Index: 6879373 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9627. Min Range: -7.9627
Max Act: 7.0252. Min Act: -0.1700
Data Index: 6879386 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9627. Min Range: -7.9627
Max Act: 6.9627. Min Act: -0.1700
Data Index: 3301434 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19