Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1696. Min Range: -5.1696
Max Act: 5.1696. Min Act: -0.1700
Data Index: 3734976 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1696. Min Range: -5.1696
Max Act: 5.1383. Min Act: -0.1700
Data Index: 5051711 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1696. Min Range: -5.1696
Max Act: 5.0133. Min Act: -0.1700
Data Index: 1256673 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.9196. Min Act: -0.1700
Data Index: 1907778 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.8883. Min Act: -0.1700
Data Index: 703653 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.8883. Min Act: -0.1700
Data Index: 4369610 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.8258. Min Act: -0.1700
Data Index: 5449007 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7946. Min Act: -0.1700
Data Index: 2849311 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.8258. Min Act: -0.1700
Data Index: 869628 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7946. Min Act: -0.1700
Data Index: 8310880 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.8258. Min Act: -0.1700
Data Index: 1530490 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7633. Min Act: -0.1700
Data Index: 3862088 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7946. Min Act: -0.1700
Data Index: 2119847 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.8258. Min Act: -0.1700
Data Index: 3538691 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7633. Min Act: -0.1700
Data Index: 6699220 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7633. Min Act: -0.1700
Data Index: 8458738 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7633. Min Act: -0.1700
Data Index: 910508 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7633. Min Act: -0.1700
Data Index: 4721840 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7321. Min Act: -0.1700
Data Index: 6172716 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1696. Min Range: -5.1696
Max Act: 4.7321. Min Act: -0.1700
Data Index: 3043415 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19