Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3753 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.4815. Min Act: -0.1700
Data Index: 6968818 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.2315. Min Act: -0.1700
Data Index: 5414028 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.1690. Min Act: -0.1700
Data Index: 6404661 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.2315. Min Act: -0.1700
Data Index: 1221180 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.2315. Min Act: -0.1700
Data Index: 1814073 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.1065. Min Act: -0.1700
Data Index: 2967457 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.1065. Min Act: -0.1700
Data Index: 5588114 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.1065. Min Act: -0.1700
Data Index: 7025755 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.1065. Min Act: -0.1700
Data Index: 6917140 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4815. Min Range: -9.4815
Max Act: 9.0440. Min Act: -0.1700
Data Index: 2690730 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9815. Min Act: -0.1700
Data Index: 1975957 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9815. Min Act: -0.1700
Data Index: 5563725 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9815. Min Act: -0.1700
Data Index: 2814024 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9190. Min Act: -0.1700
Data Index: 1351238 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9190. Min Act: -0.1700
Data Index: 7030407 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9190. Min Act: -0.1700
Data Index: 2842978 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.8565. Min Act: -0.1700
Data Index: 7835486 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9190. Min Act: -0.1700
Data Index: 5589949 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9190. Min Act: -0.1700
Data Index: 7932874 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4815. Min Range: -9.4815
Max Act: 8.9190. Min Act: -0.1700
Data Index: 4230592 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19