Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 593 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.6183. Min Act: -0.1700
Data Index: 2121912 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.4933. Min Act: -0.1700
Data Index: 241122 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.4308. Min Act: -0.1700
Data Index: 2528905 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.4308. Min Act: -0.1700
Data Index: 7236541 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.1808. Min Act: -0.1699
Data Index: 3726840 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.1183. Min Act: -0.1700
Data Index: 1478997 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.1183. Min Act: -0.1700
Data Index: 6128590 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.0558. Min Act: -0.1700
Data Index: 2673406 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9933. Min Act: -0.1700
Data Index: 2221200 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9933. Min Act: -0.1700
Data Index: 4396385 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6183. Min Range: -12.6183
Max Act: 12.0558. Min Act: -0.1700
Data Index: 8393988 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9933. Min Act: -0.1700
Data Index: 5617957 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9933. Min Act: -0.1700
Data Index: 7132642 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9933. Min Act: -0.1700
Data Index: 5839672 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9933. Min Act: -0.1700
Data Index: 1726604 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.8683. Min Act: -0.1700
Data Index: 2762451 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9308. Min Act: -0.1700
Data Index: 3071664 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9308. Min Act: -0.1700
Data Index: 1575346 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.9308. Min Act: -0.1700
Data Index: 826928 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6183. Min Range: -12.6183
Max Act: 11.8683. Min Act: -0.1700
Data Index: 3188017 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19