Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9787. Min Range: -12.9787
Max Act: 12.9787. Min Act: -0.1690
Data Index: 7141832 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.7912. Min Act: -0.1700
Data Index: 3064766 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.6037. Min Act: -0.1700
Data Index: 1288460 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.6037. Min Act: -0.1700
Data Index: 1678883 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.6662. Min Act: -0.1700
Data Index: 4406414 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.3537. Min Act: -0.1699
Data Index: 7422829 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.2287. Min Act: -0.1696
Data Index: 7254268 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.2287. Min Act: -0.1698
Data Index: 5092273 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.2287. Min Act: -0.1700
Data Index: 3183984 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.1037. Min Act: -0.1699
Data Index: 3283275 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9787. Min Range: -12.9787
Max Act: 11.0412. Min Act: -0.1700
Data Index: 3095024 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.9787. Min Act: -0.1700
Data Index: 4606300 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.9787. Min Act: -0.1700
Data Index: 2438652 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.9162. Min Act: -0.1700
Data Index: 6073562 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.8537. Min Act: -0.1699
Data Index: 4571165 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.8537. Min Act: -0.1700
Data Index: 1685272 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.7912. Min Act: -0.1700
Data Index: 1540136 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.7912. Min Act: -0.1699
Data Index: 5376770 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.7912. Min Act: -0.1700
Data Index: 5448623 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9787. Min Range: -12.9787
Max Act: 10.7287. Min Act: -0.1700
Data Index: 5354744 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19