Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5204 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.2331. Min Act: -0.1700
Data Index: 6989187 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2331. Min Range: -6.2331
Max Act: 6.0456. Min Act: -0.1700
Data Index: 8165022 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2099878 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.9831. Min Act: -0.1700
Data Index: 6938634 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.9206. Min Act: -0.1700
Data Index: 7237106 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.9206. Min Act: -0.1700
Data Index: 8041211 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8581. Min Act: -0.1700
Data Index: 2563764 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8581. Min Act: -0.1700
Data Index: 7171655 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8581. Min Act: -0.1700
Data Index: 7464597 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8581. Min Act: -0.1700
Data Index: 10363 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8268. Min Act: -0.1700
Data Index: 1059617 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8268. Min Act: -0.1700
Data Index: 4660224 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.8268. Min Act: -0.1700
Data Index: 7610845 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7643. Min Act: -0.1700
Data Index: 3552181 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7643. Min Act: -0.1700
Data Index: 6603843 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7956. Min Act: -0.1700
Data Index: 3260290 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7331. Min Act: -0.1700
Data Index: 1581149 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7331. Min Act: -0.1700
Data Index: 8044052 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7331. Min Act: -0.1700
Data Index: 4078108 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2331. Min Range: -6.2331
Max Act: 5.7643. Min Act: -0.1700
Data Index: 4351600 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19