Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3939 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2210. Min Range: -8.2210
Max Act: 8.2210. Min Act: -0.1700
Data Index: 2774337 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2210. Min Range: -8.2210
Max Act: 8.1272. Min Act: -0.1700
Data Index: 4124766 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2210. Min Range: -8.2210
Max Act: 8.0335. Min Act: -0.1700
Data Index: 5671438 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2210. Min Range: -8.2210
Max Act: 8.0335. Min Act: -0.1700
Data Index: 4416555 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.9085. Min Act: -0.1700
Data Index: 1194361 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.9085. Min Act: -0.1700
Data Index: 6998740 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.9085. Min Act: -0.1700
Data Index: 8763079 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.7835. Min Act: -0.1700
Data Index: 2716972 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.7522. Min Act: -0.1700
Data Index: 2009964 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.7210. Min Act: -0.1700
Data Index: 7422488 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.7522. Min Act: -0.1700
Data Index: 7041026 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.7210. Min Act: -0.1700
Data Index: 2555739 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.6897. Min Act: -0.1700
Data Index: 1772178 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.6272. Min Act: -0.1700
Data Index: 194665 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.6272. Min Act: -0.1700
Data Index: 2935729 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.5960. Min Act: -0.1700
Data Index: 735258 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.5647. Min Act: -0.1700
Data Index: 4229309 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.5335. Min Act: -0.1700
Data Index: 1709495 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.5647. Min Act: -0.1700
Data Index: 5881209 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2210. Min Range: -8.2210
Max Act: 7.5647. Min Act: -0.1700
Data Index: 8450950 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19