Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2651 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.5138. Min Act: -0.1700
Data Index: 5949721 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.4513. Min Act: -0.1700
Data Index: 6624322 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.3888. Min Act: -0.1700
Data Index: 4513429 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.2013. Min Act: -0.1700
Data Index: 4113051 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.2013. Min Act: -0.1700
Data Index: 8274846 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.0763. Min Act: -0.1700
Data Index: 3833555 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5138. Min Range: -8.5138
Max Act: 8.0138. Min Act: -0.1700
Data Index: 3772732 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.9513. Min Act: -0.1700
Data Index: 2210408 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.9513. Min Act: -0.1700
Data Index: 5712021 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.9513. Min Act: -0.1700
Data Index: 4513428 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.9201. Min Act: -0.1700
Data Index: 1424481 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.8576. Min Act: -0.1700
Data Index: 6809025 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.8263. Min Act: -0.1700
Data Index: 6726670 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.8263. Min Act: -0.1700
Data Index: 8090785 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.7638. Min Act: -0.1700
Data Index: 6964908 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.7326. Min Act: -0.1700
Data Index: 924549 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.7326. Min Act: -0.1700
Data Index: 2458550 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.7326. Min Act: -0.1700
Data Index: 7604259 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.7013. Min Act: -0.1700
Data Index: 8728432 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5138. Min Range: -8.5138
Max Act: 7.6701. Min Act: -0.1700
Data Index: 6265225 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19