Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1883234 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.7980. Min Act: -0.1700
Data Index: 3569630 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.7667. Min Act: -0.1700
Data Index: 3045533 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.7355. Min Act: -0.1700
Data Index: 2750086 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.7042. Min Act: -0.1699
Data Index: 4386668 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6730. Min Act: -0.1700
Data Index: 3690865 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6730. Min Act: -0.1699
Data Index: 4895327 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6730. Min Act: -0.1700
Data Index: 8288796 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6730. Min Act: -0.1700
Data Index: 1477396 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6417. Min Act: -0.1698
Data Index: 8542349 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6417. Min Act: -0.1700
Data Index: 1875904 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6105. Min Act: -0.1700
Data Index: 5817924 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6417. Min Act: -0.1700
Data Index: 4354298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6105. Min Act: -0.1699
Data Index: 5814060 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6417. Min Act: -0.1700
Data Index: 5323945 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6105. Min Act: -0.1695
Data Index: 4897473 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.5792. Min Act: -0.1700
Data Index: 2511126 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6105. Min Act: -0.1700
Data Index: 1341611 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6105. Min Act: -0.1699
Data Index: 1846199 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8292. Min Range: -5.8292
Max Act: 5.6105. Min Act: -0.1700
Data Index: 2848422 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19