Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1077 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.3927. Min Act: -0.1700
Data Index: 5983858 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.3302. Min Act: -0.1700
Data Index: 3677717 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.2365. Min Act: -0.1700
Data Index: 3929211 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.1740. Min Act: -0.1700
Data Index: 6021314 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.1740. Min Act: -0.1700
Data Index: 8760873 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.1115. Min Act: -0.1700
Data Index: 159319 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.0177. Min Act: -0.1700
Data Index: 7441753 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.9865. Min Act: -0.1700
Data Index: 1800784 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3927. Min Range: -7.3927
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2396783 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.8927. Min Act: -0.1700
Data Index: 3160047 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.8927. Min Act: -0.1700
Data Index: 827938 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.8302. Min Act: -0.1700
Data Index: 4562474 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.8302. Min Act: -0.1700
Data Index: 8527230 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.7990. Min Act: -0.1700
Data Index: 1396511 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.7052. Min Act: -0.1700
Data Index: 6351905 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.7052. Min Act: -0.1700
Data Index: 8614225 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.6740. Min Act: -0.1700
Data Index: 2713668 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.6740. Min Act: -0.1700
Data Index: 880396 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.6115. Min Act: -0.1700
Data Index: 4073532 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3927. Min Range: -7.3927
Max Act: 6.6115. Min Act: -0.1700
Data Index: 4346668 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19