Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0542. Min Range: -5.0542
Max Act: 5.0542. Min Act: -0.1700
Data Index: 3162848 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.7104. Min Act: -0.1700
Data Index: 5020017 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.7417. Min Act: -0.1700
Data Index: 5142634 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6572025 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.6479. Min Act: -0.1700
Data Index: 8610545 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.6479. Min Act: -0.1700
Data Index: 3643687 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.6479. Min Act: -0.1700
Data Index: 2746051 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5854. Min Act: -0.1700
Data Index: 3694393 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5854. Min Act: -0.1700
Data Index: 6070056 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5542. Min Act: -0.1700
Data Index: 4538299 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5229. Min Act: -0.1700
Data Index: 7860401 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5542. Min Act: -0.1700
Data Index: 7643945 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5229. Min Act: -0.1700
Data Index: 4185135 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.5229. Min Act: -0.1700
Data Index: 7198300 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.4917. Min Act: -0.1700
Data Index: 1761823 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.4917. Min Act: -0.1700
Data Index: 1233195 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.4917. Min Act: -0.1700
Data Index: 5435337 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.4917. Min Act: -0.1700
Data Index: 2831619 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.4917. Min Act: -0.1700
Data Index: 8680973 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0542. Min Range: -5.0542
Max Act: 4.4292. Min Act: -0.1700
Data Index: 1121984 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19