Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2109 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2278. Min Range: -6.2278
Max Act: 6.2278. Min Act: -0.1700
Data Index: 8081604 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2278. Min Range: -6.2278
Max Act: 6.1340. Min Act: -0.1700
Data Index: 6742999 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2278. Min Range: -6.2278
Max Act: 6.0715. Min Act: -0.1700
Data Index: 7925512 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.9465. Min Act: -0.1700
Data Index: 3273005 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.7278. Min Act: -0.1700
Data Index: 635093 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6965. Min Act: -0.1700
Data Index: 653845 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6965. Min Act: -0.1700
Data Index: 8663914 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6965. Min Act: -0.1700
Data Index: 4069241 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6965. Min Act: -0.1700
Data Index: 115043 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6965. Min Act: -0.1700
Data Index: 3557804 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6653. Min Act: -0.1700
Data Index: 3625421 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6653. Min Act: -0.1700
Data Index: 4856629 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6965. Min Act: -0.1700
Data Index: 4462787 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6340. Min Act: -0.1700
Data Index: 8351036 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6340. Min Act: -0.1700
Data Index: 142794 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6340. Min Act: -0.1700
Data Index: 4468307 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6340. Min Act: -0.1700
Data Index: 3171930 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6340. Min Act: -0.1700
Data Index: 3462919 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6340. Min Act: -0.1700
Data Index: 6898666 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2278. Min Range: -6.2278
Max Act: 5.6028. Min Act: -0.1700
Data Index: 7553014 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19