Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.6326. Min Act: -0.1700
Data Index: 1087896 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.6013. Min Act: -0.1700
Data Index: 3494399 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.5386. Min Act: -0.1700
Data Index: 8377799 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.5230. Min Act: -0.1700
Data Index: 7061676 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4917. Min Act: -0.1700
Data Index: 3225048 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4917. Min Act: -0.1700
Data Index: 7391449 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4603. Min Act: -0.1700
Data Index: 2908518 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4447. Min Act: -0.1700
Data Index: 5126019 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4290. Min Act: -0.1700
Data Index: 3149582 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4290. Min Act: -0.1700
Data Index: 601619 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4290. Min Act: -0.1700
Data Index: 2842720 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3349. Min Act: -0.1700
Data Index: 335307 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.4133. Min Act: -0.1700
Data Index: 8433088 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3349. Min Act: -0.1700
Data Index: 3575819 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3349. Min Act: -0.1700
Data Index: 4305667 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3349. Min Act: -0.1700
Data Index: 3792163 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3035. Min Act: -0.1700
Data Index: 5276241 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.2721. Min Act: -0.1700
Data Index: 1568583 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3192. Min Act: -0.1700
Data Index: 448773 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6326. Min Range: -3.6326
Max Act: 3.3035. Min Act: -0.1700
Data Index: 8025113 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19