Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7907. Min Act: -0.1700
Data Index: 7421584 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7438. Min Act: -0.1700
Data Index: 6212241 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.7125. Min Act: -0.1700
Data Index: 988772 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6499. Min Act: -0.1700
Data Index: 8308881 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.6186. Min Act: -0.1700
Data Index: 4280967 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5560. Min Act: -0.1700
Data Index: 4912664 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5873. Min Act: -0.1700
Data Index: 6934006 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5404. Min Act: -0.1700
Data Index: 4831527 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5717. Min Act: -0.1700
Data Index: 7634723 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5404. Min Act: -0.1700
Data Index: 4434898 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5247. Min Act: -0.1700
Data Index: 5422482 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.5090. Min Act: -0.1700
Data Index: 7334582 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4777. Min Act: -0.1700
Data Index: 7772923 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4620. Min Act: -0.1700
Data Index: 499440 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4777. Min Act: -0.1700
Data Index: 1269839 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4934. Min Act: -0.1700
Data Index: 5686689 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4777. Min Act: -0.1700
Data Index: 8406255 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4777. Min Act: -0.1700
Data Index: 4877494 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4777. Min Act: -0.1700
Data Index: 2463623 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7907. Min Range: -3.7907
Max Act: 3.4620. Min Act: -0.1700
Data Index: 4340620 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19