Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6022 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4345. Min Range: -7.4345
Max Act: 7.4345. Min Act: -0.1700
Data Index: 5629998 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4345. Min Range: -7.4345
Max Act: 7.3095. Min Act: -0.1700
Data Index: 6779800 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4345. Min Range: -7.4345
Max Act: 7.1845. Min Act: -0.1700
Data Index: 6375305 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.9657. Min Act: -0.1700
Data Index: 8809905 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.9657. Min Act: -0.1700
Data Index: 8028238 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.9657. Min Act: -0.1700
Data Index: 6064209 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.9345. Min Act: -0.1700
Data Index: 8448764 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.9345. Min Act: -0.1700
Data Index: 4848173 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.8720. Min Act: -0.1700
Data Index: 3179433 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.9032. Min Act: -0.1700
Data Index: 751440 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.8407. Min Act: -0.1700
Data Index: 6215316 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.8407. Min Act: -0.1700
Data Index: 4638018 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.8407. Min Act: -0.1700
Data Index: 8781498 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.7782. Min Act: -0.1700
Data Index: 8735986 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.8095. Min Act: -0.1700
Data Index: 2716579 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.7470. Min Act: -0.1700
Data Index: 617451 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.7470. Min Act: -0.1700
Data Index: 4543190 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.8095. Min Act: -0.1700
Data Index: 8522204 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.7782. Min Act: -0.1700
Data Index: 1540653 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4345. Min Range: -7.4345
Max Act: 6.7782. Min Act: -0.1700
Data Index: 8000750 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19