Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.9514. Min Act: -0.1700
Data Index: 5186633 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.9202. Min Act: -0.1700
Data Index: 7494830 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.8577. Min Act: -0.1700
Data Index: 5295408 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.8264. Min Act: -0.1700
Data Index: 1386395 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 3211145 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7327. Min Act: -0.1700
Data Index: 6322459 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7639. Min Act: -0.1700
Data Index: 2674083 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7014. Min Act: -0.1700
Data Index: 4384236 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6702. Min Act: -0.1700
Data Index: 2978811 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7014. Min Act: -0.1700
Data Index: 8330233 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7014. Min Act: -0.1700
Data Index: 5223082 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6702. Min Act: -0.1700
Data Index: 5739295 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.7014. Min Act: -0.1700
Data Index: 5975837 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6702. Min Act: -0.1700
Data Index: 4282837 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6389. Min Act: -0.1700
Data Index: 1943745 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6077. Min Act: -0.1700
Data Index: 6100241 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6389. Min Act: -0.1700
Data Index: 1065285 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6389. Min Act: -0.1700
Data Index: 309467 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6077. Min Act: -0.1700
Data Index: 1322658 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9514. Min Range: -6.9514
Max Act: 6.6077. Min Act: -0.1700
Data Index: 993738 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19