Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.7999. Min Act: -0.1700
Data Index: 6045576 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.7374. Min Act: -0.1700
Data Index: 2899776 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.7062. Min Act: -0.1700
Data Index: 4753587 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.6749. Min Act: -0.1700
Data Index: 2739938 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.6437. Min Act: -0.1700
Data Index: 7323793 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.6437. Min Act: -0.1700
Data Index: 8333385 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.6124. Min Act: -0.1700
Data Index: 6070828 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.6437. Min Act: -0.1700
Data Index: 6214845 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5812. Min Act: -0.1700
Data Index: 2260034 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5812. Min Act: -0.1700
Data Index: 1217205 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5187. Min Act: -0.1700
Data Index: 8607380 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5187. Min Act: -0.1700
Data Index: 5158566 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.4874. Min Act: -0.1700
Data Index: 8053089 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5187. Min Act: -0.1700
Data Index: 6773731 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5187. Min Act: -0.1700
Data Index: 3727522 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.5187. Min Act: -0.1700
Data Index: 3309263 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.4562. Min Act: -0.1700
Data Index: 7225678 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.4874. Min Act: -0.1700
Data Index: 432496 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.4874. Min Act: -0.1700
Data Index: 2722219 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7999. Min Range: -4.7999
Max Act: 4.4874. Min Act: -0.1700
Data Index: 4748521 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19