Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3835 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.4738. Min Act: -0.1700
Data Index: 3774033 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.2551. Min Act: -0.1700
Data Index: 3884364 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.2551. Min Act: -0.1700
Data Index: 7687462 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.1301. Min Act: -0.1700
Data Index: 4441888 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.1301. Min Act: -0.1700
Data Index: 138550 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.1301. Min Act: -0.1700
Data Index: 5751891 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.1301. Min Act: -0.1700
Data Index: 3884362 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.1301. Min Act: -0.1700
Data Index: 5019110 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.1301. Min Act: -0.1700
Data Index: 6685553 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0675. Min Act: -0.1700
Data Index: 552792 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 8297542 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 716975 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 6702230 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 1571414 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 914567 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 7200639 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0988. Min Act: -0.1700
Data Index: 5658244 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6178187 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0675. Min Act: -0.1700
Data Index: 3518099 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4738. Min Range: -4.4738
Max Act: 4.0675. Min Act: -0.1700
Data Index: 7394026 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19