Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1516 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.3271. Min Act: -0.1700
Data Index: 5935556 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 7755329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 1653210 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 7214558 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 6549005 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 3393749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 4629754 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 5932455 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 2055668 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 3493759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.2486. Min Act: -0.1700
Data Index: 7932886 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1700. Min Act: -0.1700
Data Index: 2764651 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1700. Min Act: -0.1700
Data Index: 4304090 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1857. Min Act: -0.1700
Data Index: 2280748 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1857. Min Act: -0.1700
Data Index: 1958256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1857. Min Act: -0.1700
Data Index: 8410673 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1543. Min Act: -0.1700
Data Index: 2211986 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1385. Min Act: -0.1700
Data Index: 8011515 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.0913. Min Act: -0.1700
Data Index: 7022829 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3271. Min Range: -3.3271
Max Act: 3.1385. Min Act: -0.1700
Data Index: 2622056 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19