Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.7504. Min Act: -0.1700
Data Index: 5252568 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.6566. Min Act: -0.1700
Data Index: 3638600 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.6254. Min Act: -0.1700
Data Index: 8169881 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5629. Min Act: -0.1700
Data Index: 1824944 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5316. Min Act: -0.1700
Data Index: 4424952 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5316. Min Act: -0.1700
Data Index: 2538879 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5316. Min Act: -0.1700
Data Index: 4852831 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5316. Min Act: -0.1700
Data Index: 3858003 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5004. Min Act: -0.1700
Data Index: 3149621 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5004. Min Act: -0.1700
Data Index: 5314433 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.5004. Min Act: -0.1700
Data Index: 8550304 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.4691. Min Act: -0.1700
Data Index: 2330931 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.4691. Min Act: -0.1700
Data Index: 2338793 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.4379. Min Act: -0.1700
Data Index: 2234634 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.4379. Min Act: -0.1700
Data Index: 7722640 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.4379. Min Act: -0.1700
Data Index: 6506619 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.4379. Min Act: -0.1700
Data Index: 6508769 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.3754. Min Act: -0.1700
Data Index: 5167515 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.3754. Min Act: -0.1700
Data Index: 5138194 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7504. Min Range: -6.7504
Max Act: 6.3441. Min Act: -0.1700
Data Index: 6280707 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19