Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.5394. Min Act: -0.1700
Data Index: 3028707 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.5082. Min Act: -0.1700
Data Index: 6426042 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.3519. Min Act: -0.1700
Data Index: 6753063 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.2269. Min Act: -0.1700
Data Index: 1436254 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.2269. Min Act: -0.1700
Data Index: 6088072 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.2269. Min Act: -0.1700
Data Index: 6811250 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.1332. Min Act: -0.1700
Data Index: 3279214 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.1332. Min Act: -0.1700
Data Index: 2851405 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0707. Min Act: -0.1700
Data Index: 3406184 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0707. Min Act: -0.1700
Data Index: 2103453 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.1019. Min Act: -0.1700
Data Index: 478566 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0707. Min Act: -0.1700
Data Index: 6215302 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 1941380 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 2955261 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 8366646 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 237891 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0082. Min Act: -0.1700
Data Index: 1984189 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0082. Min Act: -0.1700
Data Index: 4134337 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0394. Min Act: -0.1700
Data Index: 741476 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5394. Min Range: -6.5394
Max Act: 6.0082. Min Act: -0.1700
Data Index: 5167278 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19