Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6339. Min Range: -8.6339
Max Act: 8.6339. Min Act: -0.1700
Data Index: 370257 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.7589. Min Act: -0.1700
Data Index: 5341247 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.6964. Min Act: -0.1700
Data Index: 8674679 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.6964. Min Act: -0.1700
Data Index: 6684131 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.6964. Min Act: -0.1700
Data Index: 2265142 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.6964. Min Act: -0.1700
Data Index: 967473 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.6339. Min Act: -0.1700
Data Index: 5046645 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.6339. Min Act: -0.1700
Data Index: 5195792 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.5714. Min Act: -0.1700
Data Index: 7437232 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.5089. Min Act: -0.1700
Data Index: 5055799 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.4151. Min Act: -0.1700
Data Index: 7329980 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.3839. Min Act: -0.1700
Data Index: 8678942 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.3839. Min Act: -0.1700
Data Index: 4988297 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.3839. Min Act: -0.1700
Data Index: 2512001 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.3526. Min Act: -0.1700
Data Index: 4972755 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.3214. Min Act: -0.1700
Data Index: 3206571 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 7642441 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.2901. Min Act: -0.1700
Data Index: 1349170 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 3476841 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6339. Min Range: -8.6339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 920006 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19