Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1319 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.7224. Min Act: -0.1700
Data Index: 3448243 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.6599. Min Act: -0.1700
Data Index: 1285822 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.6286. Min Act: -0.1700
Data Index: 785323 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.5036. Min Act: -0.1700
Data Index: 4152281 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.5036. Min Act: -0.1700
Data Index: 3153705 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.4724. Min Act: -0.1700
Data Index: 1612822 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.5036. Min Act: -0.1700
Data Index: 4746404 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.4411. Min Act: -0.1700
Data Index: 2807611 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.3786. Min Act: -0.1700
Data Index: 5648891 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.3474. Min Act: -0.1700
Data Index: 6813260 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.3161. Min Act: -0.1700
Data Index: 7540344 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.2849. Min Act: -0.1700
Data Index: 3096019 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.2224. Min Act: -0.1700
Data Index: 1612820 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.2536. Min Act: -0.1700
Data Index: 7291518 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.2224. Min Act: -0.1700
Data Index: 5352387 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.2224. Min Act: -0.1700
Data Index: 1002482 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.1911. Min Act: -0.1700
Data Index: 3609805 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.1911. Min Act: -0.1700
Data Index: 839464 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.1911. Min Act: -0.1700
Data Index: 8193751 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7224. Min Range: -6.7224
Max Act: 6.1599. Min Act: -0.1700
Data Index: 281583 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19