Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.3086. Min Act: -0.1700
Data Index: 8789227 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.2461. Min Act: -0.1700
Data Index: 2365053 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.2461. Min Act: -0.1700
Data Index: 6115401 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.1524. Min Act: -0.1700
Data Index: 3542423 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.1211. Min Act: -0.1700
Data Index: 3677034 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.0899. Min Act: -0.1700
Data Index: 3401126 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.0586. Min Act: -0.1700
Data Index: 5971477 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.0274. Min Act: -0.1700
Data Index: 2153234 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9961. Min Act: -0.1700
Data Index: 4951823 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3086. Min Range: -6.3086
Max Act: 6.0274. Min Act: -0.1700
Data Index: 5894144 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9961. Min Act: -0.1700
Data Index: 4004042 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9961. Min Act: -0.1700
Data Index: 86560 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9649. Min Act: -0.1700
Data Index: 2899363 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9649. Min Act: -0.1700
Data Index: 3499392 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9336. Min Act: -0.1700
Data Index: 488771 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1408440 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1201494 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.8711. Min Act: -0.1700
Data Index: 8477370 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.8711. Min Act: -0.1700
Data Index: 8516199 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3086. Min Range: -6.3086
Max Act: 5.9024. Min Act: -0.1700
Data Index: 1465007 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19