Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2475 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.2026. Min Act: -0.1700
Data Index: 7050034 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.1401. Min Act: -0.1700
Data Index: 3381189 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.1401. Min Act: -0.1700
Data Index: 549814 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.1401. Min Act: -0.1700
Data Index: 8270933 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.1088. Min Act: -0.1700
Data Index: 6953515 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.1088. Min Act: -0.1700
Data Index: 6308704 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0776. Min Act: -0.1700
Data Index: 2459905 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.1088. Min Act: -0.1700
Data Index: 7330752 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0776. Min Act: -0.1700
Data Index: 6998664 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0151. Min Act: -0.1700
Data Index: 1531061 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0463. Min Act: -0.1700
Data Index: 4934618 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0463. Min Act: -0.1700
Data Index: 468861 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0463. Min Act: -0.1700
Data Index: 171835 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0776. Min Act: -0.1700
Data Index: 5541748 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0463. Min Act: -0.1700
Data Index: 4885230 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0463. Min Act: -0.1700
Data Index: 6785668 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2026. Min Range: -5.2026
Max Act: 4.9838. Min Act: -0.1700
Data Index: 3143010 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0151. Min Act: -0.1700
Data Index: 2400214 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0151. Min Act: -0.1700
Data Index: 5303286 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2026. Min Range: -5.2026
Max Act: 5.0151. Min Act: -0.1700
Data Index: 3255569 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19