Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.8316. Min Act: -0.1700
Data Index: 763702 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.8157. Min Act: -0.1700
Data Index: 858302 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7839. Min Act: -0.1700
Data Index: 6383335 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7520. Min Act: -0.1700
Data Index: 1868964 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7360. Min Act: -0.1700
Data Index: 6558423 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7360. Min Act: -0.1700
Data Index: 2977684 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7360. Min Act: -0.1700
Data Index: 4513432 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7200. Min Act: -0.1700
Data Index: 2592961 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7040. Min Act: -0.1700
Data Index: 2730376 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.7040. Min Act: -0.1700
Data Index: 2846274 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6720. Min Act: -0.1700
Data Index: 4990033 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6880. Min Act: -0.1700
Data Index: 7532619 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6880. Min Act: -0.1700
Data Index: 896028 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6880. Min Act: -0.1700
Data Index: 8135033 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6880. Min Act: -0.1700
Data Index: 2199141 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6720. Min Act: -0.1700
Data Index: 3403770 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6720. Min Act: -0.1700
Data Index: 3463663 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6720. Min Act: -0.1700
Data Index: 5314184 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6720. Min Act: -0.1700
Data Index: 6558424 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8316. Min Range: -2.8316
Max Act: 2.6560. Min Act: -0.1700
Data Index: 3481687 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19