Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.9916. Min Act: -0.1700
Data Index: 7265398 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8979. Min Act: -0.1700
Data Index: 4337643 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8666. Min Act: -0.1700
Data Index: 7751732 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8354. Min Act: -0.1700
Data Index: 8616504 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8354. Min Act: -0.1700
Data Index: 4522207 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8354. Min Act: -0.1700
Data Index: 6450285 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8354. Min Act: -0.1700
Data Index: 5888989 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.8041. Min Act: -0.1700
Data Index: 7138807 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7729. Min Act: -0.1700
Data Index: 1625821 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 1571538 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7729. Min Act: -0.1700
Data Index: 2317209 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 5737960 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7729. Min Act: -0.1700
Data Index: 1681111 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7729. Min Act: -0.1700
Data Index: 5179454 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 3845619 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 6458580 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 6250270 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 1876307 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 5709570 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9916. Min Range: -4.9916
Max Act: 4.7416. Min Act: -0.1700
Data Index: 5393495 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19