Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4528 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.9420. Min Act: -0.1700
Data Index: 712332 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.9108. Min Act: -0.1700
Data Index: 4579489 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.6920. Min Act: -0.1700
Data Index: 8757443 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.3170. Min Act: -0.1700
Data Index: 7552626 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.1920. Min Act: -0.1700
Data Index: 5684767 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.1920. Min Act: -0.1700
Data Index: 2852852 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.0670. Min Act: -0.1700
Data Index: 7003068 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.0358. Min Act: -0.1700
Data Index: 5235511 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.0358. Min Act: -0.1700
Data Index: 5469148 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9733. Min Act: -0.1700
Data Index: 3158259 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.0045. Min Act: -0.1700
Data Index: 2496237 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.0045. Min Act: -0.1700
Data Index: 6736948 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9420. Min Act: -0.1700
Data Index: 7986783 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9420. Min Range: -7.9420
Max Act: 7.0045. Min Act: -0.1700
Data Index: 1606418 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9420. Min Act: -0.1700
Data Index: 7126989 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9420. Min Act: -0.1700
Data Index: 2534230 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9420. Min Act: -0.1700
Data Index: 5414717 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9108. Min Act: -0.1700
Data Index: 2430895 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.8795. Min Act: -0.1700
Data Index: 3877704 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9420. Min Range: -7.9420
Max Act: 6.9108. Min Act: -0.1700
Data Index: 3735681 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19