Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3651 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.5571. Min Act: -0.1700
Data Index: 8361276 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.3384. Min Act: -0.1700
Data Index: 1779181 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.3071. Min Act: -0.1700
Data Index: 3579167 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.2446. Min Act: -0.1700
Data Index: 110703 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.2134. Min Act: -0.1700
Data Index: 1195042 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.2134. Min Act: -0.1700
Data Index: 6721884 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.1821. Min Act: -0.1700
Data Index: 2078405 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.2134. Min Act: -0.1700
Data Index: 5568136 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.1196. Min Act: -0.1700
Data Index: 3961975 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.0884. Min Act: -0.1700
Data Index: 2453267 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5571. Min Range: -7.5571
Max Act: 7.0259. Min Act: -0.1700
Data Index: 2530567 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.9946. Min Act: -0.1700
Data Index: 7307097 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.9634. Min Act: -0.1700
Data Index: 2787206 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.9009. Min Act: -0.1700
Data Index: 4409465 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.8696. Min Act: -0.1700
Data Index: 6625197 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.8696. Min Act: -0.1700
Data Index: 3943317 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.8696. Min Act: -0.1700
Data Index: 448985 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.8696. Min Act: -0.1700
Data Index: 5500823 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.8384. Min Act: -0.1700
Data Index: 792787 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5571. Min Range: -7.5571
Max Act: 6.8384. Min Act: -0.1700
Data Index: 691069 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19