Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.6494. Min Act: -0.1700
Data Index: 5370270 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.4931. Min Act: -0.1700
Data Index: 6752407 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.4931. Min Act: -0.1700
Data Index: 2351505 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.4619. Min Act: -0.1700
Data Index: 1917101 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.4619. Min Act: -0.1700
Data Index: 105825 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.4306. Min Act: -0.1700
Data Index: 305640 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3994. Min Act: -0.1700
Data Index: 3686067 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3681. Min Act: -0.1700
Data Index: 6829347 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3681. Min Act: -0.1700
Data Index: 2117566 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3681. Min Act: -0.1700
Data Index: 1957347 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3681. Min Act: -0.1700
Data Index: 2046551 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3369. Min Act: -0.1700
Data Index: 1957348 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3369. Min Act: -0.1700
Data Index: 8145792 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3369. Min Act: -0.1700
Data Index: 459878 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3369. Min Act: -0.1697
Data Index: 7253395 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3681. Min Act: -0.1700
Data Index: 2046552 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3056. Min Act: -0.1700
Data Index: 861415 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3369. Min Act: -0.1700
Data Index: 2687699 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.3056. Min Act: -0.1700
Data Index: 5165231 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6494. Min Range: -6.6494
Max Act: 6.2744. Min Act: -0.1700
Data Index: 3822837 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19