Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2598 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.7480. Min Act: -0.1700
Data Index: 4194784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.6613. Min Act: -0.1700
Data Index: 7326662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.6090. Min Act: -0.1658
Data Index: 2908451 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5566. Min Act: -0.1700
Data Index: 651813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5391. Min Act: -0.1700
Data Index: 5899973 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1700
Data Index: 7471987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1687
Data Index: 8415063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1685
Data Index: 4068223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1700
Data Index: 3814900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1638
Data Index: 3528863 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1700
Data Index: 1306787 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1697
Data Index: 3491299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1700
Data Index: 2759352 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1698
Data Index: 6649376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1687
Data Index: 1858719 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5215. Min Act: -0.1700
Data Index: 8773329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.5040. Min Act: -0.1700
Data Index: 2525140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.4688. Min Act: -0.1664
Data Index: 6804077 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.4688. Min Act: -0.1698
Data Index: 761685 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7480. Min Range: -1.7480
Max Act: 1.4337. Min Act: -0.1700
Data Index: 6388635 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19