Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2345 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.9664. Min Act: -0.1700
Data Index: 6787958 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.9352. Min Act: -0.1700
Data Index: 3513167 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.8101. Min Act: -0.1700
Data Index: 321037 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.7789. Min Act: -0.1700
Data Index: 7229871 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.7476. Min Act: -0.1700
Data Index: 4473902 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.7164. Min Act: -0.1700
Data Index: 3818518 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6851. Min Act: -0.1700
Data Index: 280420 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6851. Min Act: -0.1700
Data Index: 5691401 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6851. Min Act: -0.1700
Data Index: 5574710 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6851. Min Act: -0.1700
Data Index: 7851265 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6851. Min Act: -0.1700
Data Index: 4315407 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6851. Min Act: -0.1700
Data Index: 4527124 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6539. Min Act: -0.1700
Data Index: 332771 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6539. Min Act: -0.1700
Data Index: 8682930 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6539. Min Act: -0.1700
Data Index: 6587041 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6539. Min Act: -0.1700
Data Index: 3481445 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6226. Min Act: -0.1700
Data Index: 3294424 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6226. Min Act: -0.1700
Data Index: 5067251 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.5914. Min Act: -0.1700
Data Index: 2906197 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9664. Min Range: -4.9664
Max Act: 4.6226. Min Act: -0.1700
Data Index: 5410002 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19