Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3249. Min Range: -8.3249
Max Act: 8.3249. Min Act: -0.1700
Data Index: 1736886 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3249. Min Range: -8.3249
Max Act: 8.1999. Min Act: -0.1700
Data Index: 6771347 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3249. Min Range: -8.3249
Max Act: 8.1374. Min Act: -0.1700
Data Index: 1545340 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3249. Min Range: -8.3249
Max Act: 8.0749. Min Act: -0.1700
Data Index: 2839206 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.9499. Min Act: -0.1700
Data Index: 8145533 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.8874. Min Act: -0.1700
Data Index: 4941186 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.8249. Min Act: -0.1700
Data Index: 3811976 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.8874. Min Act: -0.1700
Data Index: 4561462 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.8249. Min Act: -0.1700
Data Index: 5846562 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.8249. Min Act: -0.1700
Data Index: 6810580 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.7624. Min Act: -0.1700
Data Index: 8197902 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.7624. Min Act: -0.1700
Data Index: 4104541 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.7312. Min Act: -0.1700
Data Index: 2647753 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.7312. Min Act: -0.1700
Data Index: 147224 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.6999. Min Act: -0.1700
Data Index: 7693334 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.6999. Min Act: -0.1700
Data Index: 2500395 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.6999. Min Act: -0.1700
Data Index: 8203347 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.6999. Min Act: -0.1700
Data Index: 7366022 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.6687. Min Act: -0.1700
Data Index: 4610581 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3249. Min Range: -8.3249
Max Act: 7.6687. Min Act: -0.1700
Data Index: 1777284 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19