Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.8410. Min Act: -0.1700
Data Index: 2237672 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.5285. Min Act: -0.1700
Data Index: 3268031 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4660. Min Act: -0.1700
Data Index: 7536543 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.4347. Min Act: -0.1700
Data Index: 1874386 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3410. Min Act: -0.1700
Data Index: 7830113 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.3097. Min Act: -0.1700
Data Index: 2967598 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.2785. Min Act: -0.1700
Data Index: 186427 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.2785. Min Act: -0.1700
Data Index: 4437577 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.2472. Min Act: -0.1700
Data Index: 3349181 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.2160. Min Act: -0.1700
Data Index: 3146369 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.2160. Min Act: -0.1700
Data Index: 2568647 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.1222. Min Act: -0.1700
Data Index: 8307169 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.1222. Min Act: -0.1700
Data Index: 8601332 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.0910. Min Act: -0.1700
Data Index: 6155984 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.0910. Min Act: -0.1700
Data Index: 7913048 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.0910. Min Act: -0.1700
Data Index: 3482657 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.0910. Min Act: -0.1700
Data Index: 8310224 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.0597. Min Act: -0.1700
Data Index: 7332663 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.1222. Min Act: -0.1700
Data Index: 6271593 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8410. Min Range: -5.8410
Max Act: 5.0910. Min Act: -0.1700
Data Index: 5257271 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19