Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 197 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.7356. Min Act: -0.1700
Data Index: 3006109 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.6260. Min Act: -0.1700
Data Index: 6601031 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5947. Min Act: -0.1700
Data Index: 520745 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5634. Min Act: -0.1700
Data Index: 2944214 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5321. Min Act: -0.1700
Data Index: 6785629 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5321. Min Act: -0.1700
Data Index: 420137 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5478. Min Act: -0.1700
Data Index: 4383352 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5321. Min Act: -0.1700
Data Index: 5940428 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5165. Min Act: -0.1700
Data Index: 4935851 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5008. Min Act: -0.1700
Data Index: 4902146 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5008. Min Act: -0.1700
Data Index: 5758257 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5008. Min Act: -0.1700
Data Index: 4951576 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.5008. Min Act: -0.1700
Data Index: 2756537 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.4538. Min Act: -0.1700
Data Index: 6564299 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.4538. Min Act: -0.1700
Data Index: 4383350 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.4225. Min Act: -0.1700
Data Index: 1282061 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.4068. Min Act: -0.1700
Data Index: 4307323 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.3911. Min Act: -0.1700
Data Index: 242722 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.3911. Min Act: -0.1700
Data Index: 4638916 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7356. Min Range: -3.7356
Max Act: 3.3911. Min Act: -0.1700
Data Index: 1580417 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19