Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2751 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.6731. Min Act: -0.1700
Data Index: 3962384 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.5481. Min Act: -0.1700
Data Index: 8603981 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.5169. Min Act: -0.1700
Data Index: 7023931 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.3606. Min Act: -0.1700
Data Index: 25204 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.3606. Min Act: -0.1700
Data Index: 5513286 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.3919. Min Act: -0.1700
Data Index: 7205798 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.2356. Min Act: -0.1700
Data Index: 8676753 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.2044. Min Act: -0.1700
Data Index: 5732290 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.1419. Min Act: -0.1700
Data Index: 1549441 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.1419. Min Act: -0.1700
Data Index: 1565596 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.1731. Min Act: -0.1700
Data Index: 4064968 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.1106. Min Act: -0.1700
Data Index: 623981 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0794. Min Act: -0.1700
Data Index: 1694382 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0481. Min Act: -0.1700
Data Index: 7406922 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0169. Min Act: -0.1700
Data Index: 3822588 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0169. Min Act: -0.1700
Data Index: 1116960 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0169. Min Act: -0.1700
Data Index: 7205796 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0169. Min Act: -0.1700
Data Index: 4736346 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0169. Min Act: -0.1700
Data Index: 2033539 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6731. Min Range: -7.6731
Max Act: 7.0169. Min Act: -0.1700
Data Index: 2076935 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19