Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5229 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.7288. Min Act: -0.1700
Data Index: 4487431 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.6975. Min Act: -0.1700
Data Index: 5781392 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.6350. Min Act: -0.1700
Data Index: 6413850 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.6038. Min Act: -0.1700
Data Index: 7236108 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.5725. Min Act: -0.1700
Data Index: 2173698 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.6038. Min Act: -0.1700
Data Index: 1888756 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.6038. Min Act: -0.1700
Data Index: 741890 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.5725. Min Act: -0.1700
Data Index: 4580883 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.5725. Min Act: -0.1700
Data Index: 1229036 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.5413. Min Act: -0.1700
Data Index: 7466183 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4788. Min Act: -0.1700
Data Index: 1535640 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4788. Min Act: -0.1700
Data Index: 4486221 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4788. Min Act: -0.1700
Data Index: 4796804 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 5146715 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 4910279 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 3395228 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 1220883 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 741519 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 1912677 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7288. Min Range: -6.7288
Max Act: 6.4475. Min Act: -0.1700
Data Index: 6016871 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19