Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.1553. Min Act: -0.1700
Data Index: 6394621 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.1553. Min Act: -0.1700
Data Index: 8144346 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0928. Min Act: -0.1700
Data Index: 1527377 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0928. Min Act: -0.1698
Data Index: 5653198 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0928. Min Act: -0.1700
Data Index: 1539640 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.1240. Min Act: -0.1700
Data Index: 104183 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0928. Min Act: -0.1700
Data Index: 4642936 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0928. Min Act: -0.1700
Data Index: 517206 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0928. Min Act: -0.1700
Data Index: 291545 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0303. Min Act: -0.1700
Data Index: 5193977 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0615. Min Act: -0.1700
Data Index: 6760755 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0303. Min Act: -0.1700
Data Index: 6990639 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1553. Min Range: -5.1553
Max Act: 5.0303. Min Act: -0.1700
Data Index: 7013640 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9990. Min Act: -0.1700
Data Index: 6263271 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9990. Min Act: -0.1700
Data Index: 1595295 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9990. Min Act: -0.1700
Data Index: 8116474 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9678. Min Act: -0.1700
Data Index: 6767980 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9990. Min Act: -0.1700
Data Index: 8809905 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9990. Min Act: -0.1700
Data Index: 6451500 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1553. Min Range: -5.1553
Max Act: 4.9678. Min Act: -0.1700
Data Index: 1372001 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19