Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9207. Min Range: -9.9207
Max Act: 9.9207. Min Act: -0.1700
Data Index: 8452296 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.9832. Min Act: -0.1700
Data Index: 5269996 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.8582. Min Act: -0.1700
Data Index: 955062 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.7957. Min Act: -0.1700
Data Index: 4503513 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.7332. Min Act: -0.1700
Data Index: 4488810 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.6082. Min Act: -0.1700
Data Index: 6330957 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.4832. Min Act: -0.1700
Data Index: 2500735 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.4207. Min Act: -0.1700
Data Index: 3459790 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.4832. Min Act: -0.1700
Data Index: 8227166 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.4832. Min Act: -0.1700
Data Index: 6631430 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.3894. Min Act: -0.1700
Data Index: 7434183 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.3582. Min Act: -0.1700
Data Index: 783097 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2644. Min Act: -0.1700
Data Index: 3366021 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2644. Min Act: -0.1700
Data Index: 8059412 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2644. Min Act: -0.1700
Data Index: 4959051 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2332. Min Act: -0.1700
Data Index: 6475588 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2332. Min Act: -0.1700
Data Index: 688699 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2644. Min Act: -0.1700
Data Index: 8746835 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2019. Min Act: -0.1700
Data Index: 4544956 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9207. Min Range: -9.9207
Max Act: 8.2332. Min Act: -0.1700
Data Index: 4813900 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19