Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.5194. Min Act: -0.1700
Data Index: 3090333 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.4569. Min Act: -0.1700
Data Index: 5515787 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.3944. Min Act: -0.1700
Data Index: 5084438 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.3319. Min Act: -0.1700
Data Index: 1794303 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.2694. Min Act: -0.1700
Data Index: 4706456 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.2694. Min Act: -0.1700
Data Index: 1839789 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.2694. Min Act: -0.1700
Data Index: 3951785 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.2069. Min Act: -0.1700
Data Index: 7103077 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.1444. Min Act: -0.1700
Data Index: 1438011 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.1444. Min Act: -0.1700
Data Index: 5453402 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0819. Min Act: -0.1700
Data Index: 7548069 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0819. Min Act: -0.1700
Data Index: 2507665 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0819. Min Act: -0.1700
Data Index: 2346410 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0819. Min Act: -0.1700
Data Index: 8354630 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0819. Min Act: -0.1700
Data Index: 3252622 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0819. Min Act: -0.1700
Data Index: 8444114 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0194. Min Act: -0.1700
Data Index: 4610748 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0194. Min Act: -0.1700
Data Index: 5655335 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5194. Min Range: -8.5194
Max Act: 8.0194. Min Act: -0.1700
Data Index: 1436466 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5194. Min Range: -8.5194
Max Act: 7.9569. Min Act: -0.1700
Data Index: 284407 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19