Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0267. Min Range: -8.0267
Max Act: 8.0267. Min Act: -0.1700
Data Index: 4711597 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.7142. Min Act: -0.1700
Data Index: 5348223 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.6517. Min Act: -0.1700
Data Index: 6377839 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.5579. Min Act: -0.1700
Data Index: 4660523 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.5267. Min Act: -0.1700
Data Index: 4178714 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.4954. Min Act: -0.1700
Data Index: 2056 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.4329. Min Act: -0.1700
Data Index: 185233 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.4017. Min Act: -0.1700
Data Index: 3884262 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3392. Min Act: -0.1700
Data Index: 1858207 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3704. Min Act: -0.1700
Data Index: 4137442 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3392. Min Act: -0.1700
Data Index: 7839871 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3704. Min Act: -0.1700
Data Index: 2111035 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.4017. Min Act: -0.1700
Data Index: 1676322 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3392. Min Act: -0.1700
Data Index: 5766018 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3392. Min Act: -0.1700
Data Index: 4580293 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3392. Min Act: -0.1700
Data Index: 4687532 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3704. Min Act: -0.1700
Data Index: 2189442 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3392. Min Act: -0.1700
Data Index: 8752898 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3079. Min Act: -0.1700
Data Index: 6902670 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0267. Min Range: -8.0267
Max Act: 7.3079. Min Act: -0.1700
Data Index: 2334851 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19