Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.9685. Min Act: -0.1700
Data Index: 564696 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.7810. Min Act: -0.1700
Data Index: 7377799 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.7497. Min Act: -0.1700
Data Index: 5668524 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.7185. Min Act: -0.1700
Data Index: 6415254 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.7497. Min Act: -0.1700
Data Index: 5106762 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 774916 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 2855337 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 4122307 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.7185. Min Act: -0.1700
Data Index: 3472341 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 3338770 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 8194275 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 8032442 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 6502796 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6872. Min Act: -0.1700
Data Index: 866273 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6560. Min Act: -0.1700
Data Index: 5330307 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6560. Min Act: -0.1700
Data Index: 3077058 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6247. Min Act: -0.1700
Data Index: 301150 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6247. Min Act: -0.1700
Data Index: 2467849 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.6247. Min Act: -0.1700
Data Index: 4921497 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9685. Min Range: -4.9685
Max Act: 4.5935. Min Act: -0.1700
Data Index: 7146608 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19