Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1274 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.8019. Min Act: -0.1700
Data Index: 1372655 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.6769. Min Act: -0.1700
Data Index: 5747485 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.5831. Min Act: -0.1700
Data Index: 3408441 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.3956. Min Act: -0.1700
Data Index: 2388404 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.3644. Min Act: -0.1700
Data Index: 8034139 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.3644. Min Act: -0.1700
Data Index: 395428 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.3644. Min Act: -0.1700
Data Index: 1959956 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.3331. Min Act: -0.1700
Data Index: 5018391 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.3019. Min Act: -0.1700
Data Index: 7688339 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.2706. Min Act: -0.1700
Data Index: 7688336 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.2394. Min Act: -0.1700
Data Index: 7649791 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.2394. Min Act: -0.1700
Data Index: 5952076 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.2081. Min Act: -0.1700
Data Index: 8599404 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.2081. Min Act: -0.1700
Data Index: 3233193 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.1769. Min Act: -0.1700
Data Index: 7743995 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.1456. Min Act: -0.1700
Data Index: 6963890 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.1769. Min Act: -0.1700
Data Index: 4761630 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.0831. Min Act: -0.1700
Data Index: 819325 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.1144. Min Act: -0.1700
Data Index: 2369 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8019. Min Range: -7.8019
Max Act: 7.1144. Min Act: -0.1700
Data Index: 8242519 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19