Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3207 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.3258. Min Act: -0.1700
Data Index: 5001831 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.1695. Min Act: -0.1700
Data Index: 1830483 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.1070. Min Act: -0.1700
Data Index: 7859815 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.0758. Min Act: -0.1700
Data Index: 227921 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.0445. Min Act: -0.1700
Data Index: 3343735 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.0133. Min Act: -0.1700
Data Index: 8054812 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9820. Min Act: -0.1700
Data Index: 8803495 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9508. Min Act: -0.1700
Data Index: 3438578 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9508. Min Act: -0.1700
Data Index: 5493173 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9508. Min Act: -0.1700
Data Index: 6081645 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9508. Min Act: -0.1700
Data Index: 7038839 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9195. Min Act: -0.1700
Data Index: 4194667 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9195. Min Act: -0.1700
Data Index: 3127425 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8570. Min Act: -0.1700
Data Index: 527062 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8258. Min Act: -0.1700
Data Index: 3966330 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8258. Min Act: -0.1700
Data Index: 1463786 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7945. Min Act: -0.1700
Data Index: 8054813 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8258. Min Act: -0.1700
Data Index: 253402 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7633. Min Act: -0.1700
Data Index: 542918 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7633. Min Act: -0.1700
Data Index: 2642191 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19