Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1809 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.9515. Min Act: -0.1700
Data Index: 6816113 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.7952. Min Act: -0.1700
Data Index: 2890216 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.7952. Min Act: -0.1700
Data Index: 6863630 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.5452. Min Act: -0.1700
Data Index: 4770523 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.3265. Min Act: -0.1700
Data Index: 1066455 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.3265. Min Act: -0.1700
Data Index: 7095911 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.3265. Min Act: -0.1700
Data Index: 8745714 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.2952. Min Act: -0.1700
Data Index: 4605131 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.1702. Min Act: -0.1700
Data Index: 7624815 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.1702. Min Act: -0.1700
Data Index: 8541728 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.1390. Min Act: -0.1700
Data Index: 8407372 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.1390. Min Act: -0.1700
Data Index: 3644060 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5739314 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0452. Min Act: -0.1700
Data Index: 6029086 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0765. Min Act: -0.1700
Data Index: 5451084 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0765. Min Act: -0.1700
Data Index: 1699320 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0452. Min Act: -0.1700
Data Index: 5461509 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0452. Min Act: -0.1700
Data Index: 4365253 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0452. Min Act: -0.1700
Data Index: 4733140 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9515. Min Range: -6.9515
Max Act: 6.0452. Min Act: -0.1700
Data Index: 6897924 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19