Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3173. Min Range: -8.3173
Max Act: 8.3173. Min Act: -0.1700
Data Index: 427434 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3173. Min Range: -8.3173
Max Act: 8.1610. Min Act: -0.1700
Data Index: 5714564 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3173. Min Range: -8.3173
Max Act: 8.0673. Min Act: -0.1700
Data Index: 6682175 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.8798. Min Act: -0.1700
Data Index: 7201698 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.7548. Min Act: -0.1700
Data Index: 2852202 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.7548. Min Act: -0.1700
Data Index: 777087 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.7235. Min Act: -0.1700
Data Index: 7853489 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.6610. Min Act: -0.1700
Data Index: 1323797 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.6298. Min Act: -0.1700
Data Index: 764643 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.5673. Min Act: -0.1700
Data Index: 2309179 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.5048. Min Act: -0.1700
Data Index: 8528776 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.4735. Min Act: -0.1700
Data Index: 2039879 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.4423. Min Act: -0.1700
Data Index: 8098844 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.4110. Min Act: -0.1700
Data Index: 3893315 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.4110. Min Act: -0.1700
Data Index: 309410 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.4110. Min Act: -0.1700
Data Index: 5610568 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.3798. Min Act: -0.1700
Data Index: 8322599 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.3798. Min Act: -0.1700
Data Index: 6158457 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.3798. Min Act: -0.1700
Data Index: 5334484 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3173. Min Range: -8.3173
Max Act: 7.3485. Min Act: -0.1700
Data Index: 6557611 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19