Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.9838. Min Act: -0.1700
Data Index: 3782012 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.6400. Min Act: -0.1700
Data Index: 8031943 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.4525. Min Act: -0.1700
Data Index: 4084435 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.3588. Min Act: -0.1700
Data Index: 6861391 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.3588. Min Act: -0.1700
Data Index: 2773848 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.3275. Min Act: -0.1700
Data Index: 3404758 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2963. Min Act: -0.1700
Data Index: 5884170 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.3275. Min Act: -0.1700
Data Index: 4663462 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2963. Min Act: -0.1700
Data Index: 1318462 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2963. Min Act: -0.1700
Data Index: 1675314 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2963. Min Act: -0.1700
Data Index: 87746 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2650. Min Act: -0.1700
Data Index: 5885216 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2650. Min Act: -0.1700
Data Index: 5718139 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2650. Min Act: -0.1700
Data Index: 1549988 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2338. Min Act: -0.1700
Data Index: 5846219 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2338. Min Act: -0.1700
Data Index: 7736728 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2025. Min Act: -0.1700
Data Index: 4633673 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2025. Min Act: -0.1700
Data Index: 6506620 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2025. Min Act: -0.1700
Data Index: 404408 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9838. Min Range: -4.9838
Max Act: 4.2025. Min Act: -0.1700
Data Index: 3470801 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19