Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.9705. Min Act: -0.1700
Data Index: 8083112 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.9080. Min Act: -0.1700
Data Index: 7920381 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8767. Min Act: -0.1700
Data Index: 3676281 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8767. Min Act: -0.1700
Data Index: 4096870 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8767. Min Act: -0.1700
Data Index: 6025600 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8455. Min Act: -0.1700
Data Index: 8598295 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8455. Min Act: -0.1700
Data Index: 7360433 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8142. Min Act: -0.1700
Data Index: 159586 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8142. Min Act: -0.1700
Data Index: 8609448 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.8142. Min Act: -0.1700
Data Index: 986468 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7830. Min Act: -0.1700
Data Index: 5189900 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7830. Min Act: -0.1700
Data Index: 5584705 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7830. Min Act: -0.1700
Data Index: 784661 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7830. Min Act: -0.1700
Data Index: 156904 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7517. Min Act: -0.1700
Data Index: 5692974 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7517. Min Act: -0.1700
Data Index: 56058 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7517. Min Act: -0.1700
Data Index: 3868782 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7205. Min Act: -0.1700
Data Index: 5138935 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7205. Min Act: -0.1700
Data Index: 393684 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9705. Min Range: -4.9705
Max Act: 4.7205. Min Act: -0.1700
Data Index: 5297512 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19