Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3415 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.6664. Min Act: -0.1700
Data Index: 1344057 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.4476. Min Act: -0.1700
Data Index: 4885910 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.4164. Min Act: -0.1700
Data Index: 1925237 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.3539. Min Act: -0.1700
Data Index: 6035493 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.3226. Min Act: -0.1700
Data Index: 6166204 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.3226. Min Act: -0.1700
Data Index: 6752877 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2914. Min Act: -0.1700
Data Index: 6339477 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2914. Min Act: -0.1700
Data Index: 3461219 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2601. Min Act: -0.1700
Data Index: 4595823 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2914. Min Act: -0.1700
Data Index: 1438309 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2914. Min Act: -0.1700
Data Index: 843719 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2914. Min Act: -0.1700
Data Index: 1562159 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2914. Min Act: -0.1700
Data Index: 4039761 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2601. Min Act: -0.1700
Data Index: 6294176 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2289. Min Act: -0.1700
Data Index: 6777789 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.2289. Min Act: -0.1700
Data Index: 182304 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.1976. Min Act: -0.1700
Data Index: 2743806 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.1976. Min Act: -0.1700
Data Index: 8589803 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.1976. Min Act: -0.1700
Data Index: 7414733 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6664. Min Range: -6.6664
Max Act: 6.1351. Min Act: -0.1700
Data Index: 6977324 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19