Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6246 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3916. Min Act: -0.1700
Data Index: 1469556 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3916. Min Act: -0.1700
Data Index: 1419035 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3759. Min Act: -0.1700
Data Index: 388889 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3602. Min Act: -0.1700
Data Index: 2589368 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3602. Min Act: -0.1700
Data Index: 6420311 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3602. Min Act: -0.1700
Data Index: 106856 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.3288. Min Act: -0.1700
Data Index: 3015253 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2817. Min Act: -0.1700
Data Index: 1990101 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2974. Min Act: -0.1700
Data Index: 6960705 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2817. Min Act: -0.1700
Data Index: 8144068 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2660. Min Act: -0.1700
Data Index: 2543561 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2817. Min Act: -0.1700
Data Index: 6007579 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2817. Min Act: -0.1700
Data Index: 7421929 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2660. Min Act: -0.1700
Data Index: 1559062 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2503. Min Act: -0.1700
Data Index: 196584 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2346. Min Act: -0.1700
Data Index: 7249533 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2503. Min Act: -0.1700
Data Index: 141689 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2503. Min Act: -0.1700
Data Index: 2200501 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2346. Min Act: -0.1700
Data Index: 2904754 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3916. Min Range: -3.3916
Max Act: 3.2346. Min Act: -0.1700
Data Index: 5381377 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19