Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2051 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.7975. Min Act: -0.1700
Data Index: 4777881 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.3600. Min Act: -0.1700
Data Index: 4040771 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.2350. Min Act: -0.1700
Data Index: 2363188 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.2975. Min Act: -0.1700
Data Index: 7056192 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.2350. Min Act: -0.1700
Data Index: 5394346 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.1100. Min Act: -0.1700
Data Index: 8562767 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.1413. Min Act: -0.1700
Data Index: 8601382 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.1100. Min Act: -0.1700
Data Index: 1234270 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.1100. Min Act: -0.1700
Data Index: 1411264 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.1100. Min Act: -0.1700
Data Index: 3353745 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0788. Min Act: -0.1700
Data Index: 860654 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0788. Min Act: -0.1700
Data Index: 5115300 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0788. Min Act: -0.1700
Data Index: 6755297 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0163. Min Act: -0.1700
Data Index: 2566693 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0788. Min Act: -0.1700
Data Index: 8489005 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0788. Min Act: -0.1700
Data Index: 7337232 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0475. Min Act: -0.1700
Data Index: 7160990 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0788. Min Act: -0.1700
Data Index: 770548 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7975. Min Range: -6.7975
Max Act: 5.9850. Min Act: -0.1700
Data Index: 5687981 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7975. Min Range: -6.7975
Max Act: 6.0163. Min Act: -0.1700
Data Index: 4028863 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19