Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0815. Min Act: -0.1700
Data Index: 1820365 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0553. Min Act: -0.1700
Data Index: 3718327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0553. Min Act: -0.1700
Data Index: 5060512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0465. Min Act: -0.1700
Data Index: 6390540 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0378. Min Act: -0.1700
Data Index: 7067558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0204. Min Act: -0.1700
Data Index: 1723459 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0204. Min Act: -0.1700
Data Index: 8318283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0117. Min Act: -0.1700
Data Index: 2013523 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0117. Min Act: -0.1700
Data Index: 5849503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0117. Min Act: -0.1700
Data Index: 303963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0030. Min Act: -0.1700
Data Index: 605914 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9944. Min Act: -0.1700
Data Index: 103666 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0815. Min Range: -1.0815
Max Act: 1.0030. Min Act: -0.1700
Data Index: 1818961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9857. Min Act: -0.1700
Data Index: 2974855 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9857. Min Act: -0.1700
Data Index: 4044811 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9857. Min Act: -0.1700
Data Index: 1620702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9944. Min Act: -0.1700
Data Index: 6861985 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9857. Min Act: -0.1700
Data Index: 5443672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9857. Min Act: -0.1700
Data Index: 225305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0815. Min Range: -1.0815
Max Act: 0.9770. Min Act: -0.1700
Data Index: 4636181 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19