Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5677 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2263. Min Range: -9.2263
Max Act: 9.2263. Min Act: -0.1700
Data Index: 7102328 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2263. Min Range: -9.2263
Max Act: 9.2263. Min Act: -0.1700
Data Index: 4104852 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2263. Min Range: -9.2263
Max Act: 9.1638. Min Act: -0.1700
Data Index: 4564807 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2263. Min Range: -9.2263
Max Act: 9.0388. Min Act: -0.1700
Data Index: 6850562 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2263. Min Range: -9.2263
Max Act: 9.1013. Min Act: -0.1700
Data Index: 7846040 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2263. Min Range: -9.2263
Max Act: 9.1013. Min Act: -0.1700
Data Index: 5334425 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.9763. Min Act: -0.1700
Data Index: 4071294 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.9138. Min Act: -0.1700
Data Index: 6101798 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.8513. Min Act: -0.1700
Data Index: 2739845 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.9138. Min Act: -0.1700
Data Index: 3007908 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.8513. Min Act: -0.1700
Data Index: 4104857 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.8513. Min Act: -0.1700
Data Index: 1364377 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.7888. Min Act: -0.1700
Data Index: 6719036 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.7888. Min Act: -0.1700
Data Index: 5876946 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.7263. Min Act: -0.1700
Data Index: 5329785 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.7263. Min Act: -0.1700
Data Index: 8287608 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.6638. Min Act: -0.1700
Data Index: 7108815 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.7263. Min Act: -0.1700
Data Index: 284696 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.6638. Min Act: -0.1700
Data Index: 1693344 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2263. Min Range: -9.2263
Max Act: 8.6638. Min Act: -0.1700
Data Index: 3743509 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19