Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.7621. Min Act: -0.1700
Data Index: 975038 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6839. Min Act: -0.1700
Data Index: 5042960 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.6526. Min Act: -0.1700
Data Index: 2075067 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5431. Min Act: -0.1700
Data Index: 6194209 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.5117. Min Act: -0.1700
Data Index: 4468997 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4961. Min Act: -0.1700
Data Index: 7037360 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4961. Min Act: -0.1700
Data Index: 401281 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4647. Min Act: -0.1700
Data Index: 1442694 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4804. Min Act: -0.1700
Data Index: 4466206 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4804. Min Act: -0.1700
Data Index: 7396628 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4647. Min Act: -0.1700
Data Index: 1886894 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4491. Min Act: -0.1700
Data Index: 1513684 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4491. Min Act: -0.1700
Data Index: 7826344 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4491. Min Act: -0.1700
Data Index: 823307 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4334. Min Act: -0.1700
Data Index: 2605669 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4334. Min Act: -0.1700
Data Index: 2156605 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4334. Min Act: -0.1700
Data Index: 2977094 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4177. Min Act: -0.1700
Data Index: 2473118 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4177. Min Act: -0.1700
Data Index: 1802012 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7621. Min Range: -3.7621
Max Act: 3.4021. Min Act: -0.1700
Data Index: 5434711 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19