Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2938 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1957. Min Range: -6.1957
Max Act: 6.1957. Min Act: -0.1700
Data Index: 7370143 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.9145. Min Act: -0.1700
Data Index: 7515200 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.9145. Min Act: -0.1700
Data Index: 6234087 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.7895. Min Act: -0.1700
Data Index: 5024825 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.8520. Min Act: -0.1700
Data Index: 5539412 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.7582. Min Act: -0.1700
Data Index: 6878922 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.6957. Min Act: -0.1700
Data Index: 730621 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.6957. Min Act: -0.1700
Data Index: 3772170 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.6020. Min Act: -0.1700
Data Index: 7740226 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5707. Min Act: -0.1700
Data Index: 310321 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5395. Min Act: -0.1700
Data Index: 5791575 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5395. Min Act: -0.1700
Data Index: 301322 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5395. Min Act: -0.1700
Data Index: 8062096 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5395. Min Act: -0.1700
Data Index: 7456885 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5707. Min Act: -0.1700
Data Index: 6789731 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5395. Min Act: -0.1700
Data Index: 1113369 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5082. Min Act: -0.1700
Data Index: 6666578 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.5395. Min Act: -0.1700
Data Index: 8453810 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.4457. Min Act: -0.1700
Data Index: 2534763 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1957. Min Range: -6.1957
Max Act: 5.4770. Min Act: -0.1700
Data Index: 1722864 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19