Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.5850. Min Act: -0.1700
Data Index: 2222975 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.5850. Min Act: -0.1700
Data Index: 8126817 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.5537. Min Act: -0.1700
Data Index: 5683891 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.5225. Min Act: -0.1700
Data Index: 4933012 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.4600. Min Act: -0.1700
Data Index: 801297 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.4600. Min Act: -0.1700
Data Index: 7488005 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.4287. Min Act: -0.1700
Data Index: 5743593 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.4287. Min Act: -0.1700
Data Index: 1135271 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3975. Min Act: -0.1700
Data Index: 6442046 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3662. Min Act: -0.1700
Data Index: 5579503 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3662. Min Act: -0.1700
Data Index: 2337393 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3037. Min Act: -0.1700
Data Index: 2331978 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3350. Min Act: -0.1700
Data Index: 7115194 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3662. Min Act: -0.1700
Data Index: 3065488 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3350. Min Act: -0.1700
Data Index: 5659756 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3350. Min Act: -0.1700
Data Index: 801295 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3350. Min Act: -0.1700
Data Index: 1137987 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3037. Min Act: -0.1700
Data Index: 801294 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3037. Min Act: -0.1700
Data Index: 2136323 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5850. Min Range: -5.5850
Max Act: 5.3037. Min Act: -0.1700
Data Index: 2504014 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19