Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.6057. Min Act: -0.1700
Data Index: 2424105 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5734. Min Act: -0.1700
Data Index: 8628172 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5734. Min Act: -0.1700
Data Index: 5154935 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5734. Min Act: -0.1700
Data Index: 8182372 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5734. Min Act: -0.1700
Data Index: 3995986 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5573. Min Act: -0.1700
Data Index: 39011 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5573. Min Act: -0.1700
Data Index: 8517402 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5573. Min Act: -0.1700
Data Index: 4252646 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5412. Min Act: -0.1700
Data Index: 4066690 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5734. Min Act: -0.1700
Data Index: 70123 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5412. Min Act: -0.1700
Data Index: 4613281 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5412. Min Act: -0.1700
Data Index: 8249688 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5412. Min Act: -0.1700
Data Index: 7005647 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5412. Min Act: -0.1700
Data Index: 201027 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5573. Min Act: -0.1700
Data Index: 5346486 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5734. Min Act: -0.1700
Data Index: 2718783 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5250. Min Act: -0.1700
Data Index: 8151963 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5250. Min Act: -0.1700
Data Index: 7947605 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5250. Min Act: -0.1700
Data Index: 5324370 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6057. Min Range: -2.6057
Max Act: 2.5250. Min Act: -0.1700
Data Index: 8593594 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19