Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4701 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.8221. Min Act: -0.1700
Data Index: 4743679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.6658. Min Act: -0.1700
Data Index: 7880032 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.6033. Min Act: -0.1700
Data Index: 8211893 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.6033. Min Act: -0.1700
Data Index: 7750063 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.5408. Min Act: -0.1700
Data Index: 383572 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.5408. Min Act: -0.1700
Data Index: 4035253 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.5096. Min Act: -0.1700
Data Index: 6090862 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 7750066 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 6434770 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4471. Min Act: -0.1700
Data Index: 2235868 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 8444658 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 6738998 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 5174259 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 6992475 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4783. Min Act: -0.1700
Data Index: 5411588 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4471. Min Act: -0.1700
Data Index: 560081 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4471. Min Act: -0.1700
Data Index: 3439733 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4471. Min Act: -0.1700
Data Index: 3784273 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4158. Min Act: -0.1700
Data Index: 812544 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8221. Min Range: -4.8221
Max Act: 4.4158. Min Act: -0.1700
Data Index: 1416235 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19