Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1770 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.2150. Min Act: -0.1700
Data Index: 6153784 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.1048. Min Act: -0.1700
Data Index: 7670679 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0733. Min Act: -0.1700
Data Index: 5548699 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0575. Min Act: -0.1700
Data Index: 6813655 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0575. Min Act: -0.1700
Data Index: 5761500 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0575. Min Act: -0.1700
Data Index: 4769286 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0260. Min Act: -0.1700
Data Index: 554480 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0418. Min Act: -0.1700
Data Index: 1081253 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0260. Min Act: -0.1700
Data Index: 1807004 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0260. Min Act: -0.1700
Data Index: 3435738 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0260. Min Act: -0.1700
Data Index: 3609267 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9944. Min Act: -0.1700
Data Index: 1043284 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2150. Min Range: -3.2150
Max Act: 3.0260. Min Act: -0.1700
Data Index: 2069871 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9944. Min Act: -0.1700
Data Index: 3145515 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9944. Min Act: -0.1700
Data Index: 6613907 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9944. Min Act: -0.1700
Data Index: 2336060 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9786. Min Act: -0.1700
Data Index: 2285711 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9627. Min Act: -0.1700
Data Index: 4832283 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9627. Min Act: -0.1700
Data Index: 7140314 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2150. Min Range: -3.2150
Max Act: 2.9627. Min Act: -0.1700
Data Index: 4211547 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19