Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5519 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.9953. Min Act: -0.1700
Data Index: 656042 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.5890. Min Act: -0.1700
Data Index: 2742130 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.5578. Min Act: -0.1700
Data Index: 7256736 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.5265. Min Act: -0.1700
Data Index: 6687184 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.5265. Min Act: -0.1700
Data Index: 1505587 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.4015. Min Act: -0.1700
Data Index: 8416995 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.3078. Min Act: -0.1700
Data Index: 3362011 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.2765. Min Act: -0.1700
Data Index: 8459234 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.2140. Min Act: -0.1700
Data Index: 3243308 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.1828. Min Act: -0.1700
Data Index: 4157870 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.1515. Min Act: -0.1700
Data Index: 2406425 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.1203. Min Act: -0.1700
Data Index: 6050465 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.1203. Min Act: -0.1700
Data Index: 3413118 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.1203. Min Act: -0.1700
Data Index: 4149919 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.0578. Min Act: -0.1700
Data Index: 8511398 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.0890. Min Act: -0.1700
Data Index: 3723957 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.0578. Min Act: -0.1700
Data Index: 1694219 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.0265. Min Act: -0.1700
Data Index: 6481112 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.0265. Min Act: -0.1700
Data Index: 8812079 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9953. Min Range: -7.9953
Max Act: 7.0265. Min Act: -0.1700
Data Index: 6333352 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19