Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.9100. Min Act: -0.1700
Data Index: 8445315 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.5350. Min Act: -0.1700
Data Index: 4953113 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.4100. Min Act: -0.1700
Data Index: 2140396 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.3787. Min Act: -0.1700
Data Index: 5555519 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.3162. Min Act: -0.1700
Data Index: 1386329 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.3162. Min Act: -0.1700
Data Index: 557069 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.3162. Min Act: -0.1700
Data Index: 1946063 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.2850. Min Act: -0.1700
Data Index: 6946196 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.2537. Min Act: -0.1700
Data Index: 6042431 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.2225. Min Act: -0.1700
Data Index: 441 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1912. Min Act: -0.1700
Data Index: 4027199 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.0975. Min Act: -0.1700
Data Index: 7951164 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1600. Min Act: -0.1700
Data Index: 713652 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1912. Min Act: -0.1700
Data Index: 5583391 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1912. Min Act: -0.1700
Data Index: 406244 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1600. Min Act: -0.1700
Data Index: 50629 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1600. Min Act: -0.1700
Data Index: 3104175 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.0975. Min Act: -0.1700
Data Index: 6848104 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.0975. Min Act: -0.1700
Data Index: 7176868 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9100. Min Range: -5.9100
Max Act: 5.1287. Min Act: -0.1700
Data Index: 6883191 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19