Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1072. Min Range: -4.1072
Max Act: 4.1072. Min Act: -0.1700
Data Index: 3499744 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1072. Min Range: -4.1072
Max Act: 4.0446. Min Act: -0.1700
Data Index: 7847881 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1072. Min Range: -4.1072
Max Act: 4.0134. Min Act: -0.1700
Data Index: 3499456 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.9821. Min Act: -0.1700
Data Index: 4221675 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.9196. Min Act: -0.1700
Data Index: 586550 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.8883. Min Act: -0.1700
Data Index: 1055919 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.8258. Min Act: -0.1700
Data Index: 5365218 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.8258. Min Act: -0.1700
Data Index: 7492354 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.8258. Min Act: -0.1700
Data Index: 8526884 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7945. Min Act: -0.1700
Data Index: 7034882 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7945. Min Act: -0.1700
Data Index: 382698 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.8102. Min Act: -0.1700
Data Index: 6882850 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7945. Min Act: -0.1700
Data Index: 4770195 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7789. Min Act: -0.1700
Data Index: 6768498 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7632. Min Act: -0.1700
Data Index: 2509503 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7476. Min Act: -0.1700
Data Index: 8737418 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7632. Min Act: -0.1700
Data Index: 1965227 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7476. Min Act: -0.1700
Data Index: 5049542 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7320. Min Act: -0.1700
Data Index: 93091 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1072. Min Range: -4.1072
Max Act: 3.7320. Min Act: -0.1700
Data Index: 4375728 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19