Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2583 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4110. Min Range: -5.4110
Max Act: 5.4110. Min Act: -0.1700
Data Index: 6708391 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4110. Min Range: -5.4110
Max Act: 5.1298. Min Act: -0.1700
Data Index: 5859180 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4110. Min Range: -5.4110
Max Act: 5.0360. Min Act: -0.1700
Data Index: 8319853 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4110. Min Range: -5.4110
Max Act: 5.0360. Min Act: -0.1700
Data Index: 5019790 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4110. Min Range: -5.4110
Max Act: 5.0360. Min Act: -0.1700
Data Index: 6744208 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.9735. Min Act: -0.1700
Data Index: 3998735 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.9423. Min Act: -0.1700
Data Index: 7740467 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.9110. Min Act: -0.1700
Data Index: 4860481 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.9110. Min Act: -0.1700
Data Index: 4870960 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8798. Min Act: -0.1700
Data Index: 5460919 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8798. Min Act: -0.1700
Data Index: 1690312 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6287779 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8798. Min Act: -0.1700
Data Index: 6583726 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8798. Min Act: -0.1700
Data Index: 3067826 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8485. Min Act: -0.1700
Data Index: 2174803 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8485. Min Act: -0.1700
Data Index: 1605787 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8173. Min Act: -0.1700
Data Index: 7266196 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.8173. Min Act: -0.1700
Data Index: 3742222 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.7860. Min Act: -0.1700
Data Index: 6196737 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4110. Min Range: -5.4110
Max Act: 4.7860. Min Act: -0.1700
Data Index: 3251208 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19