Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5576 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.5641. Min Act: -0.1700
Data Index: 1691542 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.2829. Min Act: -0.1700
Data Index: 95439 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.2516. Min Act: -0.1700
Data Index: 7130661 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.2516. Min Act: -0.1700
Data Index: 1236300 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.2204. Min Act: -0.1700
Data Index: 2339736 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.1579. Min Act: -0.1700
Data Index: 965596 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.1266. Min Act: -0.1700
Data Index: 546351 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.1579. Min Act: -0.1700
Data Index: 4040382 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0954. Min Act: -0.1700
Data Index: 7430529 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0954. Min Act: -0.1700
Data Index: 2802462 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0641. Min Act: -0.1700
Data Index: 4772344 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0329. Min Act: -0.1700
Data Index: 5848090 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0641. Min Act: -0.1700
Data Index: 2050685 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0329. Min Act: -0.1700
Data Index: 2620391 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0329. Min Act: -0.1700
Data Index: 4997998 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0329. Min Act: -0.1700
Data Index: 7927900 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0016. Min Act: -0.1700
Data Index: 5527944 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0016. Min Act: -0.1700
Data Index: 1990232 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0016. Min Act: -0.1700
Data Index: 7138112 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5641. Min Range: -6.5641
Max Act: 6.0016. Min Act: -0.1700
Data Index: 2040386 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19