Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 844 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0742. Min Act: -0.1697
Data Index: 4792162 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0574. Min Act: -0.1700
Data Index: 5941035 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0405. Min Act: -0.1700
Data Index: 2001461 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0237. Min Act: -0.1700
Data Index: 326449 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0405. Min Act: -0.1700
Data Index: 2582653 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0237. Min Act: -0.1700
Data Index: 5805696 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 4992766 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 2679126 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 1814256 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 6405688 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 3639828 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 2830116 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0237. Min Act: -0.1700
Data Index: 2783951 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0742. Min Range: -2.0742
Max Act: 1.9899. Min Act: -0.1700
Data Index: 8515351 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0742. Min Range: -2.0742
Max Act: 2.0068. Min Act: -0.1700
Data Index: 2981428 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0742. Min Range: -2.0742
Max Act: 1.9899. Min Act: -0.1700
Data Index: 4764019 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0742. Min Range: -2.0742
Max Act: 1.9899. Min Act: -0.1700
Data Index: 5530285 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0742. Min Range: -2.0742
Max Act: 1.9899. Min Act: -0.1700
Data Index: 3085412 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0742. Min Range: -2.0742
Max Act: 1.9899. Min Act: -0.1700
Data Index: 3048779 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0742. Min Range: -2.0742
Max Act: 1.9730. Min Act: -0.1700
Data Index: 1008305 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19