Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.3769. Min Act: -0.1700
Data Index: 1068796 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3769. Min Range: -4.3769
Max Act: 4.0331. Min Act: -0.1700
Data Index: 2223567 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.7986. Min Act: -0.1700
Data Index: 5043197 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.7517. Min Act: -0.1700
Data Index: 5135214 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.6891. Min Act: -0.1700
Data Index: 4331867 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.6422. Min Act: -0.1700
Data Index: 5172794 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.6265. Min Act: -0.1700
Data Index: 7136820 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5796. Min Act: -0.1700
Data Index: 7919620 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5796. Min Act: -0.1700
Data Index: 639720 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5796. Min Act: -0.1700
Data Index: 6352102 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5639. Min Act: -0.1700
Data Index: 8082147 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5952. Min Act: -0.1700
Data Index: 4063362 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5483. Min Act: -0.1700
Data Index: 5156717 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5326. Min Act: -0.1700
Data Index: 3421890 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5169. Min Act: -0.1700
Data Index: 7409506 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5326. Min Act: -0.1700
Data Index: 4924753 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5169. Min Act: -0.1700
Data Index: 673635 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5326. Min Act: -0.1700
Data Index: 5332248 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5169. Min Act: -0.1700
Data Index: 6173351 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3769. Min Range: -4.3769
Max Act: 3.5013. Min Act: -0.1700
Data Index: 4542348 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19