Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5499 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.4825. Min Act: -0.1700
Data Index: 2793834 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4825. Min Range: -7.4825
Max Act: 7.2012. Min Act: -0.1700
Data Index: 8645097 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8575. Min Act: -0.1700
Data Index: 7447902 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.8262. Min Act: -0.1700
Data Index: 7029916 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.7325. Min Act: -0.1700
Data Index: 6703138 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.7325. Min Act: -0.1700
Data Index: 7022597 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.7325. Min Act: -0.1700
Data Index: 7789822 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.7012. Min Act: -0.1700
Data Index: 7509538 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.6700. Min Act: -0.1700
Data Index: 1416034 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.6075. Min Act: -0.1700
Data Index: 17229 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.6387. Min Act: -0.1700
Data Index: 5470142 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 1558917 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 5206458 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 5912802 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 6484111 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.4825. Min Act: -0.1700
Data Index: 8548690 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.5137. Min Act: -0.1700
Data Index: 7985601 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.4512. Min Act: -0.1700
Data Index: 943223 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.4825. Min Act: -0.1700
Data Index: 4675140 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4825. Min Range: -7.4825
Max Act: 6.4512. Min Act: -0.1700
Data Index: 2987980 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19