Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5395 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.9991. Min Act: -0.1700
Data Index: 1433747 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.9991. Min Act: -0.1700
Data Index: 2145442 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.9053. Min Act: -0.1700
Data Index: 1627737 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.9053. Min Act: -0.1700
Data Index: 4928290 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.8116. Min Act: -0.1700
Data Index: 4326034 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7803. Min Act: -0.1700
Data Index: 2271871 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7803. Min Act: -0.1700
Data Index: 8457120 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7491. Min Act: -0.1700
Data Index: 7114237 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7491. Min Act: -0.1700
Data Index: 719655 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7491. Min Act: -0.1700
Data Index: 7228633 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7491. Min Act: -0.1700
Data Index: 6968794 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7178. Min Act: -0.1700
Data Index: 8427403 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.7178. Min Act: -0.1700
Data Index: 3671145 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6866. Min Act: -0.1700
Data Index: 6623757 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6866. Min Act: -0.1700
Data Index: 1333913 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6866. Min Act: -0.1700
Data Index: 4714090 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6866. Min Act: -0.1700
Data Index: 2985154 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6553. Min Act: -0.1700
Data Index: 2063940 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6553. Min Act: -0.1700
Data Index: 3394068 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9991. Min Range: -5.9991
Max Act: 5.6553. Min Act: -0.1700
Data Index: 6938767 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19