Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.6011. Min Act: -0.1699
Data Index: 5199447 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5836. Min Act: -0.1700
Data Index: 6886965 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5749. Min Act: -0.1699
Data Index: 2297335 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5662. Min Act: -0.1700
Data Index: 8481192 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5574. Min Act: -0.1674
Data Index: 7740274 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5311. Min Act: -0.1700
Data Index: 6220961 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5311. Min Act: -0.1699
Data Index: 3046928 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5311. Min Act: -0.1693
Data Index: 1771278 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5224. Min Act: -0.1700
Data Index: 7766745 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5136. Min Act: -0.1698
Data Index: 1667540 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5311. Min Act: -0.1700
Data Index: 6625702 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5224. Min Act: -0.1700
Data Index: 87155 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5136. Min Act: -0.1700
Data Index: 5210673 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5048. Min Act: -0.1595
Data Index: 6436430 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5136. Min Act: -0.1700
Data Index: 3595023 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.4960. Min Act: -0.1698
Data Index: 7354116 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.5048. Min Act: -0.1700
Data Index: 2491437 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.4960. Min Act: -0.1700
Data Index: 5167523 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.4960. Min Act: -0.1700
Data Index: 7105108 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6011. Min Range: -1.6011
Max Act: 1.4960. Min Act: -0.1700
Data Index: 5835649 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19