Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 318 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2346. Min Range: -8.2346
Max Act: 8.2346. Min Act: -0.1700
Data Index: 2185329 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.7971. Min Act: -0.1700
Data Index: 5040726 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.7971. Min Act: -0.1700
Data Index: 336357 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.6096. Min Act: -0.1700
Data Index: 3279890 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.5783. Min Act: -0.1700
Data Index: 8547860 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.4221. Min Act: -0.1700
Data Index: 4895435 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.4221. Min Act: -0.1700
Data Index: 6086566 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3908. Min Act: -0.1700
Data Index: 8407016 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3908. Min Act: -0.1700
Data Index: 7073081 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3908. Min Act: -0.1700
Data Index: 2116871 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3908. Min Act: -0.1700
Data Index: 155377 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3283. Min Act: -0.1700
Data Index: 6858369 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3283. Min Act: -0.1700
Data Index: 4560726 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.3283. Min Act: -0.1700
Data Index: 1250752 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.2658. Min Act: -0.1700
Data Index: 3005457 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.2033. Min Act: -0.1700
Data Index: 8642114 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.2346. Min Act: -0.1700
Data Index: 5735631 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5040727 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.1721. Min Act: -0.1700
Data Index: 6980733 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2346. Min Range: -8.2346
Max Act: 7.1408. Min Act: -0.1700
Data Index: 5142221 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19