Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4605 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.4839. Min Act: -0.1700
Data Index: 5926410 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.3277. Min Act: -0.1700
Data Index: 2475700 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.1402. Min Act: -0.1700
Data Index: 2802150 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.1402. Min Act: -0.1700
Data Index: 472492 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.0464. Min Act: -0.1700
Data Index: 7128258 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.0152. Min Act: -0.1700
Data Index: 3666096 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4839. Min Range: -6.4839
Max Act: 6.0152. Min Act: -0.1700
Data Index: 536890 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9839. Min Act: -0.1700
Data Index: 943046 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9214. Min Act: -0.1700
Data Index: 8602858 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9214. Min Act: -0.1700
Data Index: 1495708 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9214. Min Act: -0.1700
Data Index: 8300117 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9214. Min Act: -0.1700
Data Index: 1809828 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9214. Min Act: -0.1700
Data Index: 1205753 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.8902. Min Act: -0.1700
Data Index: 8777864 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.9527. Min Act: -0.1700
Data Index: 8630491 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.8902. Min Act: -0.1700
Data Index: 2364747 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.8277. Min Act: -0.1700
Data Index: 7919256 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.8589. Min Act: -0.1700
Data Index: 6937361 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.8277. Min Act: -0.1700
Data Index: 4219177 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4839. Min Range: -6.4839
Max Act: 5.8277. Min Act: -0.1700
Data Index: 2188781 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19