Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1857 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1320. Min Range: -7.1320
Max Act: 7.1320. Min Act: -0.1700
Data Index: 771055 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1320. Min Range: -7.1320
Max Act: 7.0695. Min Act: -0.1700
Data Index: 6621463 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.8195. Min Act: -0.1700
Data Index: 7101539 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.7570. Min Act: -0.1700
Data Index: 749844 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.7570. Min Act: -0.1700
Data Index: 2122616 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.7258. Min Act: -0.1700
Data Index: 1566442 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.7258. Min Act: -0.1700
Data Index: 117993 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6945. Min Act: -0.1700
Data Index: 4901130 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6945. Min Act: -0.1700
Data Index: 6841826 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6945. Min Act: -0.1700
Data Index: 5319454 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6633. Min Act: -0.1700
Data Index: 7653961 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6945. Min Act: -0.1700
Data Index: 4171656 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6633. Min Act: -0.1700
Data Index: 1031598 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6633. Min Act: -0.1700
Data Index: 2292530 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6633. Min Act: -0.1700
Data Index: 6181304 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6320. Min Act: -0.1700
Data Index: 3680747 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6320. Min Act: -0.1700
Data Index: 517958 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6008. Min Act: -0.1700
Data Index: 4082 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6008. Min Act: -0.1700
Data Index: 7430263 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1320. Min Range: -7.1320
Max Act: 6.6008. Min Act: -0.1700
Data Index: 8032782 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19