Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2637 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.6650. Min Act: -0.1700
Data Index: 3056375 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.6040. Min Act: -0.1700
Data Index: 861020 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.6040. Min Act: -0.1700
Data Index: 8168869 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5865. Min Act: -0.1700
Data Index: 5583307 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5865. Min Act: -0.1700
Data Index: 6584325 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5778. Min Act: -0.1700
Data Index: 8131031 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5603. Min Act: -0.1700
Data Index: 1825460 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5778. Min Act: -0.1700
Data Index: 7030491 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5515. Min Act: -0.1700
Data Index: 3787968 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5603. Min Act: -0.1700
Data Index: 2950536 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5690. Min Act: -0.1700
Data Index: 3935679 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5515. Min Act: -0.1700
Data Index: 2678141 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5603. Min Act: -0.1699
Data Index: 6261187 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5603. Min Act: -0.1700
Data Index: 3516646 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5515. Min Act: -0.1700
Data Index: 652172 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5515. Min Act: -0.1700
Data Index: 4863988 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5515. Min Act: -0.1700
Data Index: 343926 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5428. Min Act: -0.1700
Data Index: 3954410 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5515. Min Act: -0.1700
Data Index: 1114169 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6650. Min Range: -1.6650
Max Act: 1.5603. Min Act: -0.1700
Data Index: 7504993 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19