Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8945. Min Act: -0.1700
Data Index: 32134 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8945. Min Act: -0.1700
Data Index: 1828825 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8786. Min Act: -0.1700
Data Index: 2130151 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8468. Min Act: -0.1700
Data Index: 1382320 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8309. Min Act: -0.1700
Data Index: 1881560 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8309. Min Act: -0.1700
Data Index: 958037 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8309. Min Act: -0.1700
Data Index: 3921973 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7991. Min Act: -0.1700
Data Index: 4897002 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7991. Min Act: -0.1700
Data Index: 845532 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8150. Min Act: -0.1700
Data Index: 2627420 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.8150. Min Act: -0.1700
Data Index: 5641182 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7991. Min Act: -0.1700
Data Index: 7637714 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7991. Min Act: -0.1700
Data Index: 2921068 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7832. Min Act: -0.1700
Data Index: 1493737 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7832. Min Act: -0.1700
Data Index: 6152376 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7832. Min Act: -0.1700
Data Index: 353973 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7672. Min Act: -0.1700
Data Index: 408528 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7672. Min Act: -0.1700
Data Index: 284188 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7672. Min Act: -0.1700
Data Index: 733780 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8945. Min Range: -2.8945
Max Act: 2.7513. Min Act: -0.1700
Data Index: 244903 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19