Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2006 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.9295. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.7062. Min Act: -0.1700
Data Index: 858250 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6541. Min Act: -0.1700
Data Index: 2063767 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6715. Min Act: -0.1700
Data Index: 2178948 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6367. Min Act: -0.1700
Data Index: 7159816 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6193. Min Act: -0.1700
Data Index: 5746224 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6193. Min Act: -0.1700
Data Index: 4806594 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6367. Min Act: -0.1700
Data Index: 727121 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 1707824 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 826205 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 7587021 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 3762447 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 5976464 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 7854460 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.6018. Min Act: -0.1700
Data Index: 2571697 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.5843. Min Act: -0.1700
Data Index: 3621774 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.5843. Min Act: -0.1700
Data Index: 7192573 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.5843. Min Act: -0.1700
Data Index: 2180980 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.5843. Min Act: -0.1700
Data Index: 3563801 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9295. Min Range: -1.9295
Max Act: 1.5843. Min Act: -0.1700
Data Index: 1986900 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19