Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 873 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0604. Min Range: -4.0604
Max Act: 4.0604. Min Act: -0.1700
Data Index: 7261132 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0604. Min Range: -4.0604
Max Act: 4.0292. Min Act: -0.1700
Data Index: 3293161 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9979. Min Act: -0.1700
Data Index: 6500536 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9979. Min Act: -0.1700
Data Index: 6690782 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9979. Min Act: -0.1700
Data Index: 2084236 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9979. Min Act: -0.1700
Data Index: 4275592 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9979. Min Act: -0.1700
Data Index: 6717561 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9354. Min Act: -0.1700
Data Index: 7350220 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9354. Min Act: -0.1700
Data Index: 1643610 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9667. Min Act: -0.1700
Data Index: 4474161 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9354. Min Act: -0.1700
Data Index: 5749525 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9041. Min Act: -0.1700
Data Index: 1249077 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8729. Min Act: -0.1700
Data Index: 4077981 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8729. Min Act: -0.1700
Data Index: 4455435 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.9041. Min Act: -0.1700
Data Index: 2497103 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8729. Min Act: -0.1700
Data Index: 2456525 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8729. Min Act: -0.1700
Data Index: 7876583 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8729. Min Act: -0.1700
Data Index: 6154616 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8416. Min Act: -0.1700
Data Index: 2151197 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0604. Min Range: -4.0604
Max Act: 3.8416. Min Act: -0.1700
Data Index: 7264311 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19