Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5790 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.7961. Min Act: -0.1700
Data Index: 5753452 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.6711. Min Act: -0.1700
Data Index: 2218217 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5773. Min Act: -0.1700
Data Index: 1379460 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5773. Min Act: -0.1700
Data Index: 5378422 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5461. Min Act: -0.1700
Data Index: 4123590 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5461. Min Act: -0.1700
Data Index: 80319 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5148. Min Act: -0.1700
Data Index: 789418 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5148. Min Act: -0.1700
Data Index: 4209478 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5148. Min Act: -0.1700
Data Index: 5438364 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5148. Min Act: -0.1700
Data Index: 1653895 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.4836. Min Act: -0.1700
Data Index: 1217656 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.4836. Min Act: -0.1700
Data Index: 5271076 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.4836. Min Act: -0.1700
Data Index: 8093333 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.5148. Min Act: -0.1700
Data Index: 8433523 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.4523. Min Act: -0.1700
Data Index: 6806095 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.4211. Min Act: -0.1700
Data Index: 2838473 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.4211. Min Act: -0.1700
Data Index: 1833143 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.3898. Min Act: -0.1700
Data Index: 1227890 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.3898. Min Act: -0.1700
Data Index: 4813973 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7961. Min Range: -6.7961
Max Act: 6.3586. Min Act: -0.1700
Data Index: 2268849 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19