Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.6454. Min Act: -0.1700
Data Index: 463746 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.4266. Min Act: -0.1700
Data Index: 53030 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.4266. Min Act: -0.1700
Data Index: 5563641 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.3954. Min Act: -0.1700
Data Index: 6142347 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.3016. Min Act: -0.1700
Data Index: 703421 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.3016. Min Act: -0.1700
Data Index: 3106575 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2704. Min Act: -0.1700
Data Index: 3252426 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.3016. Min Act: -0.1700
Data Index: 2060650 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.3016. Min Act: -0.1700
Data Index: 908487 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2704. Min Act: -0.1700
Data Index: 6326871 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2704. Min Act: -0.1700
Data Index: 3854047 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2704. Min Act: -0.1700
Data Index: 3883787 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2391. Min Act: -0.1700
Data Index: 1052881 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2704. Min Act: -0.1700
Data Index: 7905234 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2079. Min Act: -0.1700
Data Index: 5670524 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2079. Min Act: -0.1700
Data Index: 8300258 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.2079. Min Act: -0.1700
Data Index: 1642575 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.1766. Min Act: -0.1700
Data Index: 439525 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.1141. Min Act: -0.1700
Data Index: 45889 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6454. Min Range: -5.6454
Max Act: 5.1454. Min Act: -0.1700
Data Index: 1314130 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19