Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0708. Min Range: -8.0708
Max Act: 8.0708. Min Act: -0.1700
Data Index: 1936967 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0708. Min Range: -8.0708
Max Act: 8.0395. Min Act: -0.1700
Data Index: 6700438 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.8833. Min Act: -0.1700
Data Index: 6458601 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.8520. Min Act: -0.1700
Data Index: 4004447 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.7583. Min Act: -0.1700
Data Index: 6383428 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.7583. Min Act: -0.1700
Data Index: 1397732 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.6645. Min Act: -0.1700
Data Index: 1740057 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.6333. Min Act: -0.1700
Data Index: 1502083 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.5708. Min Act: -0.1700
Data Index: 2656820 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.5083. Min Act: -0.1700
Data Index: 383470 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.4770. Min Act: -0.1700
Data Index: 5822481 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.4770. Min Act: -0.1700
Data Index: 958910 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.4770. Min Act: -0.1700
Data Index: 618843 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.4145. Min Act: -0.1700
Data Index: 4301443 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.4145. Min Act: -0.1700
Data Index: 2841493 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.4145. Min Act: -0.1700
Data Index: 1069539 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.3833. Min Act: -0.1700
Data Index: 2312348 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.3833. Min Act: -0.1700
Data Index: 2824314 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.3833. Min Act: -0.1700
Data Index: 5850994 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0708. Min Range: -8.0708
Max Act: 7.3833. Min Act: -0.1700
Data Index: 8478004 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19