Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4230 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0972. Min Act: -0.1700
Data Index: 6013480 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0972. Min Act: -0.1700
Data Index: 215836 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0814. Min Act: -0.1700
Data Index: 5916161 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.1129. Min Act: -0.1700
Data Index: 607193 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0814. Min Act: -0.1700
Data Index: 8324127 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0657. Min Act: -0.1700
Data Index: 8223676 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0657. Min Act: -0.1700
Data Index: 2388688 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0499. Min Act: -0.1700
Data Index: 457881 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1129. Min Range: -3.1129
Max Act: 3.0341. Min Act: -0.1700
Data Index: 2278175 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9867. Min Act: -0.1700
Data Index: 2020224 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9867. Min Act: -0.1700
Data Index: 7356102 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9709. Min Act: -0.1700
Data Index: 5591207 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9551. Min Act: -0.1700
Data Index: 3552555 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9392. Min Act: -0.1700
Data Index: 3641687 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9075. Min Act: -0.1700
Data Index: 2676899 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9234. Min Act: -0.1700
Data Index: 1309114 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9234. Min Act: -0.1700
Data Index: 5402070 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9392. Min Act: -0.1700
Data Index: 3034773 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9234. Min Act: -0.1700
Data Index: 7916156 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1129. Min Range: -3.1129
Max Act: 2.9234. Min Act: -0.1700
Data Index: 5687623 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19