Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.7138. Min Act: -0.1700
Data Index: 699496 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.4638. Min Act: -0.1700
Data Index: 806938 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.4326. Min Act: -0.1700
Data Index: 3943089 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.4013. Min Act: -0.1700
Data Index: 8562915 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.3701. Min Act: -0.1700
Data Index: 1822928 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.3388. Min Act: -0.1700
Data Index: 1252023 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.3388. Min Act: -0.1700
Data Index: 3187544 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.3388. Min Act: -0.1700
Data Index: 2275812 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.3388. Min Act: -0.1700
Data Index: 6374615 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2763. Min Act: -0.1700
Data Index: 6043824 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2763. Min Act: -0.1700
Data Index: 3818007 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2763. Min Act: -0.1700
Data Index: 3604558 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2763. Min Act: -0.1700
Data Index: 8051314 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2451. Min Act: -0.1700
Data Index: 7636476 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2451. Min Act: -0.1700
Data Index: 2034172 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2138. Min Act: -0.1700
Data Index: 1618112 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.2138. Min Act: -0.1700
Data Index: 4217076 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.1826. Min Act: -0.1700
Data Index: 3296886 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.1826. Min Act: -0.1700
Data Index: 7211975 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7138. Min Range: -6.7138
Max Act: 6.1513. Min Act: -0.1700
Data Index: 4446447 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19