Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5315 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.4538. Min Act: -0.1700
Data Index: 5180496 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.4538. Min Act: -0.1700
Data Index: 5141346 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.2976. Min Act: -0.1700
Data Index: 5633423 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.3601. Min Act: -0.1700
Data Index: 118936 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.2663. Min Act: -0.1700
Data Index: 2918677 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.0788. Min Act: -0.1700
Data Index: 3245676 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.0788. Min Act: -0.1700
Data Index: 425882 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.0788. Min Act: -0.1700
Data Index: 8311708 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4538. Min Range: -6.4538
Max Act: 6.0476. Min Act: -0.1700
Data Index: 5382825 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9851. Min Act: -0.1700
Data Index: 896557 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9851. Min Act: -0.1700
Data Index: 4602598 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9851. Min Act: -0.1700
Data Index: 882142 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9851. Min Act: -0.1700
Data Index: 5067732 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9538. Min Act: -0.1700
Data Index: 5701180 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9226. Min Act: -0.1700
Data Index: 5298974 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.8913. Min Act: -0.1700
Data Index: 6861297 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9226. Min Act: -0.1700
Data Index: 5438585 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.9538. Min Act: -0.1700
Data Index: 8700402 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.8601. Min Act: -0.1700
Data Index: 1686100 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4538. Min Range: -6.4538
Max Act: 5.8913. Min Act: -0.1700
Data Index: 239165 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19