Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2960 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.6925. Min Act: -0.1700
Data Index: 2598552 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.5986. Min Act: -0.1700
Data Index: 462155 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.5829. Min Act: -0.1700
Data Index: 790362 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.5516. Min Act: -0.1700
Data Index: 1632782 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.5360. Min Act: -0.1700
Data Index: 3531060 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.5360. Min Act: -0.1700
Data Index: 608607 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4890. Min Act: -0.1700
Data Index: 3839200 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.5203. Min Act: -0.1700
Data Index: 5099598 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4733. Min Act: -0.1700
Data Index: 7307768 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4263. Min Act: -0.1700
Data Index: 7056295 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4577. Min Act: -0.1700
Data Index: 4586247 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4263. Min Act: -0.1700
Data Index: 2157620 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4420. Min Act: -0.1700
Data Index: 8735144 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4577. Min Act: -0.1700
Data Index: 1584870 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4106. Min Act: -0.1700
Data Index: 1346700 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4106. Min Act: -0.1700
Data Index: 3387684 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4106. Min Act: -0.1700
Data Index: 651050 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4263. Min Act: -0.1700
Data Index: 1171996 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.3950. Min Act: -0.1700
Data Index: 1809226 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6925. Min Range: -3.6925
Max Act: 3.4263. Min Act: -0.1700
Data Index: 2044436 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19