Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.6594. Min Act: -0.1700
Data Index: 1284672 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5951. Min Act: -0.1700
Data Index: 2493177 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5951. Min Act: -0.1700
Data Index: 6059378 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5629. Min Act: -0.1700
Data Index: 6571909 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5790. Min Act: -0.1700
Data Index: 2388992 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5629. Min Act: -0.1700
Data Index: 2755009 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5467. Min Act: -0.1700
Data Index: 3189839 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5467. Min Act: -0.1700
Data Index: 7957118 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5467. Min Act: -0.1700
Data Index: 6571910 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5467. Min Act: -0.1700
Data Index: 4076691 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5629. Min Act: -0.1700
Data Index: 5129775 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5467. Min Act: -0.1700
Data Index: 3239606 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5144. Min Act: -0.1700
Data Index: 5635348 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5306. Min Act: -0.1700
Data Index: 996836 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5467. Min Act: -0.1700
Data Index: 6245518 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5306. Min Act: -0.1700
Data Index: 528661 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5144. Min Act: -0.1700
Data Index: 367795 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5306. Min Act: -0.1700
Data Index: 6911949 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5306. Min Act: -0.1700
Data Index: 247977 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6594. Min Range: -2.6594
Max Act: 2.5306. Min Act: -0.1700
Data Index: 5027531 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19