Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5897 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.2384. Min Act: -0.1700
Data Index: 1651508 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.2072. Min Act: -0.1700
Data Index: 6340998 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.2072. Min Act: -0.1700
Data Index: 4293042 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.2072. Min Act: -0.1700
Data Index: 5065885 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.1134. Min Act: -0.1700
Data Index: 805987 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.0509. Min Act: -0.1700
Data Index: 6859005 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2384. Min Range: -5.2384
Max Act: 5.0197. Min Act: -0.1700
Data Index: 6859006 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.9572. Min Act: -0.1700
Data Index: 4606799 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.9259. Min Act: -0.1700
Data Index: 2631467 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.8634. Min Act: -0.1700
Data Index: 6067609 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.8634. Min Act: -0.1700
Data Index: 607580 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.8322. Min Act: -0.1700
Data Index: 2631336 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.8009. Min Act: -0.1700
Data Index: 5376106 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.8009. Min Act: -0.1700
Data Index: 3640949 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.7384. Min Act: -0.1700
Data Index: 7141292 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.7384. Min Act: -0.1700
Data Index: 101867 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.7384. Min Act: -0.1700
Data Index: 3568527 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.7384. Min Act: -0.1700
Data Index: 7541967 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.7384. Min Act: -0.1700
Data Index: 7573111 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2384. Min Range: -5.2384
Max Act: 4.7384. Min Act: -0.1700
Data Index: 6067608 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19