Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5259 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.6574. Min Act: -0.1700
Data Index: 6280204 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.4074. Min Act: -0.1700
Data Index: 36944 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.4074. Min Act: -0.1700
Data Index: 4100489 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.3449. Min Act: -0.1700
Data Index: 4675125 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.0949. Min Act: -0.1700
Data Index: 8475662 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.0949. Min Act: -0.1700
Data Index: 595519 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.0637. Min Act: -0.1700
Data Index: 8410728 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.0637. Min Act: -0.1700
Data Index: 4395962 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.0324. Min Act: -0.1700
Data Index: 4154913 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6574. Min Range: -8.6574
Max Act: 8.0324. Min Act: -0.1700
Data Index: 8213069 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.9699. Min Act: -0.1700
Data Index: 2188457 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.9074. Min Act: -0.1700
Data Index: 5284096 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.8137. Min Act: -0.1700
Data Index: 1196962 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.8137. Min Act: -0.1700
Data Index: 5059128 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.7824. Min Act: -0.1700
Data Index: 3145737 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.7824. Min Act: -0.1700
Data Index: 7198262 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.7512. Min Act: -0.1700
Data Index: 5164987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.7512. Min Act: -0.1700
Data Index: 1619269 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.7199. Min Act: -0.1700
Data Index: 3345844 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6574. Min Range: -8.6574
Max Act: 7.6887. Min Act: -0.1700
Data Index: 4687797 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19