Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2749 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7017. Min Range: -7.7017
Max Act: 7.7017. Min Act: -0.1700
Data Index: 5958310 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7017. Min Range: -7.7017
Max Act: 7.2642. Min Act: -0.1700
Data Index: 2281148 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7017. Min Range: -7.7017
Max Act: 7.1704. Min Act: -0.1700
Data Index: 736878 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7017. Min Range: -7.7017
Max Act: 7.2017. Min Act: -0.1700
Data Index: 4944449 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7017. Min Range: -7.7017
Max Act: 7.1392. Min Act: -0.1700
Data Index: 3240795 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7017. Min Range: -7.7017
Max Act: 7.0142. Min Act: -0.1700
Data Index: 2405382 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.9204. Min Act: -0.1700
Data Index: 7483044 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.8267. Min Act: -0.1700
Data Index: 416230 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.8267. Min Act: -0.1700
Data Index: 2224514 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.8267. Min Act: -0.1700
Data Index: 7626900 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.8267. Min Act: -0.1700
Data Index: 7483045 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.7017. Min Act: -0.1700
Data Index: 164048 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.6392. Min Act: -0.1700
Data Index: 2520927 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.7017. Min Act: -0.1700
Data Index: 4214512 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.7017. Min Act: -0.1700
Data Index: 888128 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.7017. Min Act: -0.1700
Data Index: 7015438 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.6392. Min Act: -0.1700
Data Index: 5015743 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.6392. Min Act: -0.1700
Data Index: 4944451 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.6704. Min Act: -0.1700
Data Index: 4255104 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7017. Min Range: -7.7017
Max Act: 6.6704. Min Act: -0.1700
Data Index: 501262 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19