Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.9525. Min Act: -0.1700
Data Index: 4718451 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.7338. Min Act: -0.1700
Data Index: 8149609 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.6400. Min Act: -0.1700
Data Index: 1850802 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.4838. Min Act: -0.1700
Data Index: 1023099 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.4213. Min Act: -0.1700
Data Index: 1532717 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.3588. Min Act: -0.1700
Data Index: 7128155 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.3588. Min Act: -0.1700
Data Index: 4741723 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.3275. Min Act: -0.1700
Data Index: 2320324 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2963. Min Act: -0.1700
Data Index: 4770038 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2963. Min Act: -0.1700
Data Index: 3752198 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2338. Min Act: -0.1700
Data Index: 3553169 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2025. Min Act: -0.1700
Data Index: 6352080 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2338. Min Act: -0.1700
Data Index: 1808298 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2025. Min Act: -0.1700
Data Index: 8559933 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.2025. Min Act: -0.1700
Data Index: 3774312 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.1713. Min Act: -0.1700
Data Index: 360705 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.1713. Min Act: -0.1700
Data Index: 8822080 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.1400. Min Act: -0.1700
Data Index: 2309032 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.1400. Min Act: -0.1700
Data Index: 7098551 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9525. Min Range: -6.9525
Max Act: 6.1400. Min Act: -0.1700
Data Index: 178408 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19