Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5907 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.2385. Min Act: -0.1700
Data Index: 6843821 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2385. Min Range: -8.2385
Max Act: 8.1135. Min Act: -0.1700
Data Index: 3310699 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.5510. Min Act: -0.1700
Data Index: 2245104 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.4573. Min Act: -0.1700
Data Index: 817527 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.3635. Min Act: -0.1700
Data Index: 8091318 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.2073. Min Act: -0.1700
Data Index: 7198766 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.1448. Min Act: -0.1700
Data Index: 8001539 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.1448. Min Act: -0.1700
Data Index: 2604010 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.1448. Min Act: -0.1700
Data Index: 673112 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.1135. Min Act: -0.1700
Data Index: 4988472 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.0823. Min Act: -0.1700
Data Index: 7927036 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.0823. Min Act: -0.1700
Data Index: 3389538 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.0510. Min Act: -0.1700
Data Index: 58113 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.0198. Min Act: -0.1700
Data Index: 5816083 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.0198. Min Act: -0.1700
Data Index: 4399009 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2385. Min Range: -8.2385
Max Act: 6.9885. Min Act: -0.1700
Data Index: 8005110 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2385. Min Range: -8.2385
Max Act: 6.9885. Min Act: -0.1700
Data Index: 8395048 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2385. Min Range: -8.2385
Max Act: 6.9885. Min Act: -0.1700
Data Index: 930495 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2385. Min Range: -8.2385
Max Act: 7.0198. Min Act: -0.1700
Data Index: 5567173 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2385. Min Range: -8.2385
Max Act: 6.9885. Min Act: -0.1700
Data Index: 386183 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19