Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1404 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0043. Min Range: -7.0043
Max Act: 7.0043. Min Act: -0.1700
Data Index: 4092208 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.9418. Min Act: -0.1700
Data Index: 5692505 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.8481. Min Act: -0.1700
Data Index: 7561169 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.8168. Min Act: -0.1700
Data Index: 8615946 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.7856. Min Act: -0.1700
Data Index: 5060719 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.7543. Min Act: -0.1700
Data Index: 1456490 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.7543. Min Act: -0.1700
Data Index: 6852388 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.7231. Min Act: -0.1700
Data Index: 6605525 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.7231. Min Act: -0.1700
Data Index: 8483362 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.7231. Min Act: -0.1700
Data Index: 2819873 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.6918. Min Act: -0.1700
Data Index: 8034892 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.6918. Min Act: -0.1700
Data Index: 7028070 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.6918. Min Act: -0.1700
Data Index: 7234073 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.6606. Min Act: -0.1700
Data Index: 8615949 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.6293. Min Act: -0.1700
Data Index: 8736651 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.5981. Min Act: -0.1700
Data Index: 7699917 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.6293. Min Act: -0.1700
Data Index: 1742307 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.5668. Min Act: -0.1700
Data Index: 1875082 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.5668. Min Act: -0.1700
Data Index: 6230993 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0043. Min Range: -7.0043
Max Act: 6.5668. Min Act: -0.1700
Data Index: 2902735 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19