Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5552 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.2176. Min Act: -0.1700
Data Index: 3768869 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.2176. Min Act: -0.1700
Data Index: 4107342 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1863. Min Act: -0.1700
Data Index: 850395 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1551. Min Act: -0.1700
Data Index: 6962084 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1551. Min Act: -0.1700
Data Index: 5216101 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1551. Min Act: -0.1700
Data Index: 4606231 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1340974 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0926. Min Act: -0.1700
Data Index: 2840471 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1551. Min Act: -0.1700
Data Index: 599959 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1238. Min Act: -0.1700
Data Index: 3306381 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1238. Min Act: -0.1700
Data Index: 8305690 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1238. Min Act: -0.1700
Data Index: 7380225 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.1238. Min Act: -0.1700
Data Index: 5277537 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0926. Min Act: -0.1700
Data Index: 1769715 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0926. Min Act: -0.1700
Data Index: 5718507 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0926. Min Act: -0.1700
Data Index: 3508276 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0926. Min Act: -0.1700
Data Index: 3922750 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0613. Min Act: -0.1700
Data Index: 8589589 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0613. Min Act: -0.1700
Data Index: 6323458 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2176. Min Range: -5.2176
Max Act: 5.0613. Min Act: -0.1700
Data Index: 5902015 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19