Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.9168. Min Act: -0.1700
Data Index: 6346455 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.9168. Min Act: -0.1700
Data Index: 7271441 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6980. Min Act: -0.1700
Data Index: 5208357 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6668. Min Act: -0.1700
Data Index: 5821936 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6668. Min Act: -0.1700
Data Index: 1647500 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6355. Min Act: -0.1700
Data Index: 1099331 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6355. Min Act: -0.1700
Data Index: 3192402 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6355. Min Act: -0.1700
Data Index: 4267184 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6043. Min Act: -0.1700
Data Index: 2334700 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.5730. Min Act: -0.1700
Data Index: 3875056 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.6043. Min Act: -0.1700
Data Index: 3620903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.5730. Min Act: -0.1700
Data Index: 4562606 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.5418. Min Act: -0.1700
Data Index: 3935944 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.5418. Min Act: -0.1700
Data Index: 1956282 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.5105. Min Act: -0.1700
Data Index: 1118837 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.4793. Min Act: -0.1700
Data Index: 7004907 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.4793. Min Act: -0.1700
Data Index: 1041131 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.4793. Min Act: -0.1700
Data Index: 974421 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.4793. Min Act: -0.1700
Data Index: 1988289 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9168. Min Range: -5.9168
Max Act: 5.4793. Min Act: -0.1700
Data Index: 5956901 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19