Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1607 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1706. Min Range: -8.1706
Max Act: 8.1706. Min Act: -0.1700
Data Index: 6302315 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1706. Min Range: -8.1706
Max Act: 8.0769. Min Act: -0.1700
Data Index: 8578980 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.8894. Min Act: -0.1700
Data Index: 1787794 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.8581. Min Act: -0.1700
Data Index: 4658284 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7956. Min Act: -0.1700
Data Index: 585950 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.8269. Min Act: -0.1700
Data Index: 7296784 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7956. Min Act: -0.1700
Data Index: 8578981 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7956. Min Act: -0.1700
Data Index: 6985944 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7644. Min Act: -0.1700
Data Index: 6887915 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7331. Min Act: -0.1700
Data Index: 3062802 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7644. Min Act: -0.1700
Data Index: 404108 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.7331. Min Act: -0.1700
Data Index: 7564255 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6706. Min Act: -0.1700
Data Index: 4841356 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6706. Min Act: -0.1700
Data Index: 8137384 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6706. Min Act: -0.1700
Data Index: 4451685 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6394. Min Act: -0.1700
Data Index: 2861568 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6706. Min Act: -0.1700
Data Index: 5290166 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6394. Min Act: -0.1700
Data Index: 5499379 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.6081. Min Act: -0.1700
Data Index: 597401 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1706. Min Range: -8.1706
Max Act: 7.5769. Min Act: -0.1700
Data Index: 5820983 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19