Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5119 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.7197. Min Act: -0.1700
Data Index: 3528690 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.6885. Min Act: -0.1700
Data Index: 474007 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.6572. Min Act: -0.1700
Data Index: 3585932 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.6260. Min Act: -0.1700
Data Index: 5981919 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.6260. Min Act: -0.1700
Data Index: 3176570 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.6260. Min Act: -0.1700
Data Index: 1170724 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5635. Min Act: -0.1700
Data Index: 3337131 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5635. Min Act: -0.1700
Data Index: 3186516 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5635. Min Act: -0.1700
Data Index: 3733194 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5635. Min Act: -0.1700
Data Index: 4379261 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5322. Min Act: -0.1700
Data Index: 5005952 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5322. Min Act: -0.1700
Data Index: 1869136 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5010. Min Act: -0.1700
Data Index: 6623171 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5010. Min Act: -0.1700
Data Index: 7601227 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5010. Min Act: -0.1700
Data Index: 3883224 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5010. Min Act: -0.1700
Data Index: 4752036 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.5010. Min Act: -0.1700
Data Index: 956998 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.4697. Min Act: -0.1700
Data Index: 5661469 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.4385. Min Act: -0.1700
Data Index: 2498611 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7197. Min Range: -5.7197
Max Act: 5.4697. Min Act: -0.1700
Data Index: 5918675 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19