Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.4257. Min Act: -0.1700
Data Index: 7738425 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2845. Min Act: -0.1700
Data Index: 8522484 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2688. Min Act: -0.1700
Data Index: 3310610 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2531. Min Act: -0.1700
Data Index: 8522480 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2217. Min Act: -0.1700
Data Index: 5051285 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2060. Min Act: -0.1700
Data Index: 5051280 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2060. Min Act: -0.1700
Data Index: 5216267 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2060. Min Act: -0.1700
Data Index: 6249816 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2060. Min Act: -0.1700
Data Index: 3214504 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1745. Min Act: -0.1700
Data Index: 6016663 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1903. Min Act: -0.1700
Data Index: 5634889 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.2060. Min Act: -0.1700
Data Index: 2456478 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1903. Min Act: -0.1700
Data Index: 6674958 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1745. Min Act: -0.1700
Data Index: 4257635 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1745. Min Act: -0.1700
Data Index: 5736452 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1745. Min Act: -0.1700
Data Index: 4768489 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1588. Min Act: -0.1700
Data Index: 6249815 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1273. Min Act: -0.1700
Data Index: 2917510 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1430. Min Act: -0.1700
Data Index: 938246 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4257. Min Range: -3.4257
Max Act: 3.1430. Min Act: -0.1700
Data Index: 8478418 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19