Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 8605200 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.5727. Min Act: -0.1700
Data Index: 3036422 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.5102. Min Act: -0.1700
Data Index: 6091050 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4477. Min Act: -0.1700
Data Index: 5101446 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4477. Min Act: -0.1700
Data Index: 6206244 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4477. Min Act: -0.1700
Data Index: 4356019 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3852. Min Act: -0.1700
Data Index: 5490773 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4164. Min Act: -0.1700
Data Index: 4114952 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.4164. Min Act: -0.1700
Data Index: 2033846 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3852. Min Act: -0.1700
Data Index: 4323583 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3852. Min Act: -0.1700
Data Index: 2614408 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3227. Min Act: -0.1700
Data Index: 1104385 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.3227. Min Act: -0.1700
Data Index: 4715709 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2602. Min Act: -0.1700
Data Index: 1988257 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2602. Min Act: -0.1700
Data Index: 8532840 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2602. Min Act: -0.1700
Data Index: 985910 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2602. Min Act: -0.1700
Data Index: 3983774 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2289. Min Act: -0.1700
Data Index: 4541578 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.2289. Min Act: -0.1700
Data Index: 4059949 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6352. Min Range: -5.6352
Max Act: 5.1977. Min Act: -0.1700
Data Index: 5010139 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19