Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1883 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.9831. Min Act: -0.1700
Data Index: 5439348 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.9206. Min Act: -0.1700
Data Index: 6060785 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.8581. Min Act: -0.1700
Data Index: 8080366 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.8269. Min Act: -0.1700
Data Index: 685418 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.8269. Min Act: -0.1700
Data Index: 645483 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.7956. Min Act: -0.1700
Data Index: 4700593 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.7644. Min Act: -0.1700
Data Index: 7175514 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.7019. Min Act: -0.1700
Data Index: 2527263 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.6394. Min Act: -0.1700
Data Index: 7338741 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.6081. Min Act: -0.1700
Data Index: 5518933 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.6081. Min Act: -0.1700
Data Index: 5828647 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.6394. Min Act: -0.1700
Data Index: 7335985 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5769. Min Act: -0.1700
Data Index: 6239565 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5769. Min Act: -0.1700
Data Index: 5627554 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5769. Min Act: -0.1700
Data Index: 1612542 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5456. Min Act: -0.1700
Data Index: 4588959 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5456. Min Act: -0.1700
Data Index: 1057589 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5144. Min Act: -0.1700
Data Index: 7268911 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.5144. Min Act: -0.1700
Data Index: 2024478 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9831. Min Range: -6.9831
Max Act: 6.4831. Min Act: -0.1700
Data Index: 1210582 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19