Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7875. Min Act: -0.1700
Data Index: 872388 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7875. Min Act: -0.1700
Data Index: 8551654 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7250. Min Act: -0.1700
Data Index: 4776283 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7250. Min Act: -0.1700
Data Index: 5276839 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7250. Min Act: -0.1700
Data Index: 4194608 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7250. Min Act: -0.1700
Data Index: 3009412 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.7250. Min Act: -0.1700
Data Index: 593606 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6937. Min Act: -0.1700
Data Index: 3979773 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6937. Min Act: -0.1700
Data Index: 2790803 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6234406 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6937. Min Act: -0.1700
Data Index: 7245391 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6937. Min Act: -0.1700
Data Index: 2134982 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6500407 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 2749229 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6814643 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 5691432 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 4020715 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 2999745 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6625. Min Act: -0.1700
Data Index: 5429607 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7875. Min Range: -5.7875
Max Act: 5.6312. Min Act: -0.1700
Data Index: 2127399 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19