Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.5219. Min Act: -0.1700
Data Index: 1217786 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.5219. Min Act: -0.1700
Data Index: 797509 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.2407. Min Act: -0.1700
Data Index: 7007074 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.1782. Min Act: -0.1700
Data Index: 8830079 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.1157. Min Act: -0.1700
Data Index: 581069 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.1469. Min Act: -0.1700
Data Index: 6702808 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.1157. Min Act: -0.1700
Data Index: 8301011 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.0844. Min Act: -0.1700
Data Index: 7309606 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.0532. Min Act: -0.1700
Data Index: 5079098 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5219. Min Range: -7.5219
Max Act: 7.1157. Min Act: -0.1700
Data Index: 2188158 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.9594. Min Act: -0.1700
Data Index: 7564240 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.9594. Min Act: -0.1700
Data Index: 991461 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.9594. Min Act: -0.1700
Data Index: 7769662 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.9594. Min Act: -0.1700
Data Index: 1298132 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.8969. Min Act: -0.1700
Data Index: 2767510 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.9282. Min Act: -0.1700
Data Index: 8145789 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.8969. Min Act: -0.1700
Data Index: 8265438 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.8969. Min Act: -0.1700
Data Index: 7173139 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.8657. Min Act: -0.1700
Data Index: 7316309 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5219. Min Range: -7.5219
Max Act: 6.8657. Min Act: -0.1700
Data Index: 4029479 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19