Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6314 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.9835. Min Act: -0.1700
Data Index: 7567904 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.8585. Min Act: -0.1700
Data Index: 6902066 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 7090020 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 4765284 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 2638835 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 5563602 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 7178688 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.6710. Min Act: -0.1700
Data Index: 3627976 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.6710. Min Act: -0.1700
Data Index: 2103024 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.6085. Min Act: -0.1700
Data Index: 524082 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.6085. Min Act: -0.1700
Data Index: 6859790 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.4210. Min Act: -0.1700
Data Index: 2071931 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.3585. Min Act: -0.1700
Data Index: 7656348 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.2960. Min Act: -0.1700
Data Index: 887665 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.2960. Min Act: -0.1700
Data Index: 4591621 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.3585. Min Act: -0.1700
Data Index: 1075032 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.2335. Min Act: -0.1700
Data Index: 2314156 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.2335. Min Act: -0.1700
Data Index: 4333250 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.2335. Min Act: -0.1700
Data Index: 2849491 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9835. Min Range: -8.9835
Max Act: 8.2960. Min Act: -0.1700
Data Index: 2877553 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19