Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2557 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.9258. Min Act: -0.1700
Data Index: 8664922 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.9570. Min Act: -0.1700
Data Index: 4274649 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.8320. Min Act: -0.1700
Data Index: 443674 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.8320. Min Act: -0.1700
Data Index: 2168489 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.7695. Min Act: -0.1700
Data Index: 4149305 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.7070. Min Act: -0.1700
Data Index: 6635995 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.7070. Min Act: -0.1700
Data Index: 2169419 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6445. Min Act: -0.1700
Data Index: 6571576 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6445. Min Act: -0.1700
Data Index: 7999964 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6445. Min Act: -0.1700
Data Index: 7422748 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6133. Min Act: -0.1700
Data Index: 2524714 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6133. Min Act: -0.1700
Data Index: 8827126 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6133. Min Act: -0.1700
Data Index: 1379432 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6133. Min Act: -0.1700
Data Index: 642112 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6133. Min Act: -0.1700
Data Index: 6705656 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.5508. Min Act: -0.1700
Data Index: 4720199 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.5820. Min Act: -0.1700
Data Index: 5010817 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.5508. Min Act: -0.1700
Data Index: 3662971 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.6133. Min Act: -0.1700
Data Index: 794504 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9570. Min Range: -4.9570
Max Act: 4.5820. Min Act: -0.1700
Data Index: 1961587 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19