Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0858. Min Range: -5.0858
Max Act: 5.0858. Min Act: -0.1700
Data Index: 2195980 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0858. Min Range: -5.0858
Max Act: 5.0545. Min Act: -0.1700
Data Index: 4125135 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0858. Min Range: -5.0858
Max Act: 5.0545. Min Act: -0.1700
Data Index: 4136625 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0858. Min Range: -5.0858
Max Act: 5.0233. Min Act: -0.1700
Data Index: 1502913 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9920. Min Act: -0.1700
Data Index: 4578391 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9920. Min Act: -0.1700
Data Index: 1340292 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9920. Min Act: -0.1700
Data Index: 535019 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9608. Min Act: -0.1700
Data Index: 77229 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9920. Min Act: -0.1700
Data Index: 3348157 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9608. Min Act: -0.1700
Data Index: 4085034 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9295. Min Act: -0.1700
Data Index: 59508 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9295. Min Act: -0.1700
Data Index: 8377188 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9295. Min Act: -0.1700
Data Index: 1340289 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9295. Min Act: -0.1700
Data Index: 4625509 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.9295. Min Act: -0.1700
Data Index: 5067876 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.8983. Min Act: -0.1700
Data Index: 59504 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.8983. Min Act: -0.1700
Data Index: 1564407 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.8983. Min Act: -0.1700
Data Index: 6503964 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.8983. Min Act: -0.1700
Data Index: 3854680 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.8670. Min Act: -0.1700
Data Index: 7379073 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19