Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.8366. Min Act: -0.1700
Data Index: 4374913 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.8053. Min Act: -0.1700
Data Index: 4367507 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7427. Min Act: -0.1700
Data Index: 4125925 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.7115. Min Act: -0.1700
Data Index: 8673198 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.6645. Min Act: -0.1700
Data Index: 8667407 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.6332. Min Act: -0.1700
Data Index: 6078383 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.6176. Min Act: -0.1700
Data Index: 5364183 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.6019. Min Act: -0.1700
Data Index: 951135 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.6019. Min Act: -0.1700
Data Index: 572626 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5706. Min Act: -0.1700
Data Index: 1970961 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5706. Min Act: -0.1700
Data Index: 3967361 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5706. Min Act: -0.1700
Data Index: 7444077 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5550. Min Act: -0.1700
Data Index: 6833263 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5706. Min Act: -0.1700
Data Index: 2017104 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5550. Min Act: -0.1700
Data Index: 5376034 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5550. Min Act: -0.1700
Data Index: 2921986 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5550. Min Act: -0.1700
Data Index: 2444859 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5237. Min Act: -0.1700
Data Index: 8054297 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5237. Min Act: -0.1700
Data Index: 1937266 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8366. Min Range: -3.8366
Max Act: 3.5080. Min Act: -0.1700
Data Index: 4657275 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19