Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.3640. Min Act: -0.1700
Data Index: 8679261 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.3327. Min Act: -0.1700
Data Index: 3311489 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.3015. Min Act: -0.1700
Data Index: 1538719 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2702. Min Act: -0.1700
Data Index: 4640944 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2702. Min Act: -0.1700
Data Index: 6388531 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2390. Min Act: -0.1700
Data Index: 2589844 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2390. Min Act: -0.1700
Data Index: 5885984 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2702. Min Act: -0.1700
Data Index: 5218555 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2077. Min Act: -0.1700
Data Index: 6095503 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2077. Min Act: -0.1700
Data Index: 7993923 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.2077. Min Act: -0.1700
Data Index: 2466676 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1765. Min Act: -0.1700
Data Index: 4020902 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1765. Min Act: -0.1700
Data Index: 8460688 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1140. Min Act: -0.1700
Data Index: 1225994 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1452. Min Act: -0.1700
Data Index: 5590115 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1452. Min Act: -0.1700
Data Index: 4866109 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.0827. Min Act: -0.1700
Data Index: 4354703 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1140. Min Act: -0.1700
Data Index: 5386862 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1140. Min Act: -0.1700
Data Index: 5800273 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3640. Min Range: -5.3640
Max Act: 5.1140. Min Act: -0.1700
Data Index: 215358 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19