Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.9598. Min Act: -0.1700
Data Index: 5595937 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.8973. Min Act: -0.1700
Data Index: 3245142 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.8035. Min Act: -0.1700
Data Index: 242182 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.8035. Min Act: -0.1700
Data Index: 1352020 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.7723. Min Act: -0.1700
Data Index: 5595927 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.8035. Min Act: -0.1700
Data Index: 5595943 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.7410. Min Act: -0.1700
Data Index: 7695663 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.7098. Min Act: -0.1700
Data Index: 7427553 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.7410. Min Act: -0.1700
Data Index: 3245141 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.7410. Min Act: -0.1700
Data Index: 3245143 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.6160. Min Act: -0.1700
Data Index: 2229582 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5535. Min Act: -0.1700
Data Index: 6307129 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5535. Min Act: -0.1700
Data Index: 619232 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5223. Min Act: -0.1700
Data Index: 4318754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5535. Min Act: -0.1700
Data Index: 5595932 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5535. Min Act: -0.1700
Data Index: 1381239 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5535. Min Act: -0.1700
Data Index: 6584054 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5535. Min Act: -0.1700
Data Index: 5595938 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5223. Min Act: -0.1700
Data Index: 830068 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9598. Min Range: -4.9598
Max Act: 4.5223. Min Act: -0.1700
Data Index: 5150995 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19