Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6215. Min Range: -7.6215
Max Act: 7.6215. Min Act: -0.1700
Data Index: 5292721 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6215. Min Range: -7.6215
Max Act: 7.2777. Min Act: -0.1700
Data Index: 5288330 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6215. Min Range: -7.6215
Max Act: 7.0902. Min Act: -0.1700
Data Index: 5211398 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6215. Min Range: -7.6215
Max Act: 7.0902. Min Act: -0.1700
Data Index: 8459280 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6215. Min Range: -7.6215
Max Act: 7.0590. Min Act: -0.1700
Data Index: 3110848 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.9965. Min Act: -0.1700
Data Index: 4240372 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.9027. Min Act: -0.1700
Data Index: 8655312 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.8402. Min Act: -0.1700
Data Index: 1843903 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.7777. Min Act: -0.1700
Data Index: 7262094 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.7152. Min Act: -0.1700
Data Index: 1444447 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.6215. Min Act: -0.1700
Data Index: 7693255 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.6215. Min Act: -0.1700
Data Index: 246782 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.6215. Min Act: -0.1700
Data Index: 995152 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.6215. Min Act: -0.1700
Data Index: 2509883 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.5590. Min Act: -0.1700
Data Index: 285598 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.5902. Min Act: -0.1700
Data Index: 4201232 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.4965. Min Act: -0.1700
Data Index: 5969403 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.4652. Min Act: -0.1700
Data Index: 7446217 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.4965. Min Act: -0.1700
Data Index: 7886896 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6215. Min Range: -7.6215
Max Act: 6.4652. Min Act: -0.1700
Data Index: 3997155 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19