Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2023 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1105. Min Range: -3.1105
Max Act: 3.1105. Min Act: -0.1700
Data Index: 4612825 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1105. Min Range: -3.1105
Max Act: 3.0001. Min Act: -0.1700
Data Index: 5382456 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1105. Min Range: -3.1105
Max Act: 3.0001. Min Act: -0.1700
Data Index: 8831637 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9684. Min Act: -0.1700
Data Index: 7858608 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9368. Min Act: -0.1700
Data Index: 505927 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9368. Min Act: -0.1700
Data Index: 72464 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9368. Min Act: -0.1700
Data Index: 3092674 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9209. Min Act: -0.1700
Data Index: 6849697 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9209. Min Act: -0.1700
Data Index: 5254227 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9209. Min Act: -0.1700
Data Index: 754915 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9209. Min Act: -0.1700
Data Index: 4591059 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9209. Min Act: -0.1700
Data Index: 5809268 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9209. Min Act: -0.1700
Data Index: 605272 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9051. Min Act: -0.1700
Data Index: 8503912 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.8892. Min Act: -0.1700
Data Index: 2229561 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.9051. Min Act: -0.1700
Data Index: 5376645 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.8892. Min Act: -0.1700
Data Index: 2183367 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.8734. Min Act: -0.1700
Data Index: 780945 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.8734. Min Act: -0.1700
Data Index: 2780260 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1105. Min Range: -3.1105
Max Act: 2.8575. Min Act: -0.1700
Data Index: 2506329 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19