Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2275 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2609. Min Range: -9.2609
Max Act: 9.2609. Min Act: -0.1700
Data Index: 7255875 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2609. Min Range: -9.2609
Max Act: 9.1984. Min Act: -0.1700
Data Index: 8270193 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2609. Min Range: -9.2609
Max Act: 9.1359. Min Act: -0.1700
Data Index: 7255896 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.9484. Min Act: -0.1700
Data Index: 8415132 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.9484. Min Act: -0.1700
Data Index: 2056505 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.8234. Min Act: -0.1700
Data Index: 1593819 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.8234. Min Act: -0.1700
Data Index: 7255888 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.8234. Min Act: -0.1700
Data Index: 6936349 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.6984. Min Act: -0.1700
Data Index: 671406 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.7609. Min Act: -0.1700
Data Index: 8487978 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.6984. Min Act: -0.1700
Data Index: 4835459 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.6984. Min Act: -0.1700
Data Index: 4003554 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.6359. Min Act: -0.1700
Data Index: 1412833 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.6359. Min Act: -0.1700
Data Index: 2957474 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.6359. Min Act: -0.1700
Data Index: 3822649 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.5734. Min Act: -0.1700
Data Index: 7255900 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.5734. Min Act: -0.1700
Data Index: 357511 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.5734. Min Act: -0.1700
Data Index: 3090049 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.5734. Min Act: -0.1700
Data Index: 7255885 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2609. Min Range: -9.2609
Max Act: 8.4484. Min Act: -0.1700
Data Index: 7555573 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19