Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.1169. Min Act: -0.1700
Data Index: 6459914 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1169. Min Range: -5.1169
Max Act: 5.0544. Min Act: -0.1700
Data Index: 1602667 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.9294. Min Act: -0.1700
Data Index: 5959310 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8669. Min Act: -0.1700
Data Index: 476166 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.8356. Min Act: -0.1700
Data Index: 2445566 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.7731. Min Act: -0.1700
Data Index: 2483347 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.7106. Min Act: -0.1700
Data Index: 7128892 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6794. Min Act: -0.1700
Data Index: 3970621 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6794. Min Act: -0.1700
Data Index: 2742210 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6794. Min Act: -0.1700
Data Index: 787109 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6481. Min Act: -0.1700
Data Index: 2820449 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6481. Min Act: -0.1700
Data Index: 2699960 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6169. Min Act: -0.1700
Data Index: 3306805 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6169. Min Act: -0.1700
Data Index: 7271441 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6481. Min Act: -0.1700
Data Index: 311513 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6481. Min Act: -0.1700
Data Index: 4098099 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6169. Min Act: -0.1700
Data Index: 1514588 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.6169. Min Act: -0.1700
Data Index: 456023 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.5856. Min Act: -0.1700
Data Index: 5942278 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1169. Min Range: -5.1169
Max Act: 4.5544. Min Act: -0.1700
Data Index: 5306205 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19