Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0661. Min Range: -6.0661
Max Act: 6.0661. Min Act: -0.1700
Data Index: 7660903 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.9411. Min Act: -0.1700
Data Index: 7363714 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.9098. Min Act: -0.1700
Data Index: 7128211 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.7536. Min Act: -0.1700
Data Index: 1263759 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.7223. Min Act: -0.1700
Data Index: 7897648 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6911. Min Act: -0.1700
Data Index: 5219169 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.7223. Min Act: -0.1700
Data Index: 8102709 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6911. Min Act: -0.1700
Data Index: 4537721 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6598. Min Act: -0.1700
Data Index: 2181329 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6911. Min Act: -0.1700
Data Index: 8127811 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6598. Min Act: -0.1700
Data Index: 5787674 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6598. Min Act: -0.1700
Data Index: 4761358 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6598. Min Act: -0.1700
Data Index: 3303231 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6286. Min Act: -0.1700
Data Index: 1048759 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6286. Min Act: -0.1700
Data Index: 4817175 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6286. Min Act: -0.1700
Data Index: 2756623 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6286. Min Act: -0.1700
Data Index: 4706080 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.5973. Min Act: -0.1700
Data Index: 758287 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.5973. Min Act: -0.1700
Data Index: 6524442 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0661. Min Range: -6.0661
Max Act: 5.6286. Min Act: -0.1700
Data Index: 6454227 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19