Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3037. Min Range: -9.3037
Max Act: 9.3037. Min Act: -0.1700
Data Index: 8765315 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3037. Min Range: -9.3037
Max Act: 9.0537. Min Act: -0.1700
Data Index: 6732480 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.9287. Min Act: -0.1700
Data Index: 2544571 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.9912. Min Act: -0.1700
Data Index: 1124869 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.9912. Min Act: -0.1700
Data Index: 7793502 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8662. Min Act: -0.1700
Data Index: 3104972 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.9287. Min Act: -0.1700
Data Index: 4815422 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.9287. Min Act: -0.1700
Data Index: 7795907 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8662. Min Act: -0.1700
Data Index: 6400807 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8662. Min Act: -0.1700
Data Index: 8726245 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8037. Min Act: -0.1700
Data Index: 4481489 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8037. Min Act: -0.1700
Data Index: 6400810 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8037. Min Act: -0.1700
Data Index: 2409216 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8037. Min Act: -0.1700
Data Index: 7793503 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.8037. Min Act: -0.1700
Data Index: 1248248 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.7412. Min Act: -0.1700
Data Index: 1197195 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.7412. Min Act: -0.1700
Data Index: 2526365 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.7412. Min Act: -0.1700
Data Index: 2544572 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.6787. Min Act: -0.1700
Data Index: 2013205 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3037. Min Range: -9.3037
Max Act: 8.6787. Min Act: -0.1700
Data Index: 6517055 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19