Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2710 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4389. Min Range: -7.4389
Max Act: 7.4389. Min Act: -0.1700
Data Index: 2942562 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.9702. Min Act: -0.1700
Data Index: 4355368 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.9389. Min Act: -0.1700
Data Index: 6001596 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.7827. Min Act: -0.1700
Data Index: 3053658 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.7827. Min Act: -0.1700
Data Index: 6609502 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.7514. Min Act: -0.1700
Data Index: 8828090 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.7202. Min Act: -0.1700
Data Index: 8828091 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.6889. Min Act: -0.1700
Data Index: 5200313 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5952. Min Act: -0.1700
Data Index: 8156930 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.6264. Min Act: -0.1700
Data Index: 4171675 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.6264. Min Act: -0.1700
Data Index: 1861992 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.6577. Min Act: -0.1700
Data Index: 2847615 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5952. Min Act: -0.1700
Data Index: 4503344 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5952. Min Act: -0.1700
Data Index: 8832016 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5639. Min Act: -0.1700
Data Index: 6555618 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.6264. Min Act: -0.1700
Data Index: 4889060 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5952. Min Act: -0.1700
Data Index: 6018245 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5639. Min Act: -0.1700
Data Index: 80416 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5327. Min Act: -0.1700
Data Index: 7327295 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4389. Min Range: -7.4389
Max Act: 6.5014. Min Act: -0.1700
Data Index: 4984490 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19