Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.3696. Min Act: -0.1700
Data Index: 6351900 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.2446. Min Act: -0.1700
Data Index: 2773833 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1821. Min Act: -0.1700
Data Index: 577993 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1821. Min Act: -0.1700
Data Index: 5758153 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 7816869 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 1206572 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 4774947 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 1898759 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 171804 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 6693327 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.1196. Min Act: -0.1700
Data Index: 6231868 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.0571. Min Act: -0.1700
Data Index: 1147993 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3696. Min Range: -9.3696
Max Act: 8.9946. Min Act: -0.1700
Data Index: 1672911 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.0571. Min Act: -0.1700
Data Index: 1939266 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.0571. Min Act: -0.1700
Data Index: 8752176 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3696. Min Range: -9.3696
Max Act: 9.0571. Min Act: -0.1700
Data Index: 8581419 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3696. Min Range: -9.3696
Max Act: 8.9946. Min Act: -0.1700
Data Index: 3085853 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3696. Min Range: -9.3696
Max Act: 8.9946. Min Act: -0.1700
Data Index: 1262141 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3696. Min Range: -9.3696
Max Act: 8.9946. Min Act: -0.1700
Data Index: 6785868 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3696. Min Range: -9.3696
Max Act: 8.9321. Min Act: -0.1700
Data Index: 6886772 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19