Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.3275. Min Act: -0.1700
Data Index: 7359521 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1713. Min Act: -0.1700
Data Index: 5850056 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.2025. Min Act: -0.1700
Data Index: 156842 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1400. Min Act: -0.1700
Data Index: 5966110 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1088. Min Act: -0.1700
Data Index: 8075064 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.1088. Min Act: -0.1700
Data Index: 5566758 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0775. Min Act: -0.1700
Data Index: 1940131 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0150. Min Act: -0.1700
Data Index: 2305366 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0463. Min Act: -0.1700
Data Index: 2439658 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0463. Min Act: -0.1700
Data Index: 6702632 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0463. Min Act: -0.1700
Data Index: 185868 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0150. Min Act: -0.1700
Data Index: 4555217 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0150. Min Act: -0.1700
Data Index: 2021703 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3275. Min Range: -6.3275
Max Act: 6.0150. Min Act: -0.1700
Data Index: 7096494 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9838. Min Act: -0.1700
Data Index: 7650913 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9838. Min Act: -0.1700
Data Index: 4522037 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9525. Min Act: -0.1700
Data Index: 1259926 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9525. Min Act: -0.1700
Data Index: 4444671 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9525. Min Act: -0.1700
Data Index: 7919533 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3275. Min Range: -6.3275
Max Act: 5.9525. Min Act: -0.1700
Data Index: 3818798 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19