Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1343 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0398. Min Range: -7.0398
Max Act: 7.0398. Min Act: -0.1700
Data Index: 7323382 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.8835. Min Act: -0.1700
Data Index: 804359 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.8210. Min Act: -0.1700
Data Index: 1296828 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.7585. Min Act: -0.1700
Data Index: 6709325 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.7898. Min Act: -0.1700
Data Index: 7423519 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.7273. Min Act: -0.1700
Data Index: 2872172 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.7273. Min Act: -0.1700
Data Index: 512775 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.7585. Min Act: -0.1700
Data Index: 6028137 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.7585. Min Act: -0.1700
Data Index: 5716261 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6960. Min Act: -0.1700
Data Index: 3471167 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6960. Min Act: -0.1700
Data Index: 441261 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 1548881 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 3840211 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 4801329 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 5911012 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 315454 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 2140392 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6648. Min Act: -0.1700
Data Index: 1676257 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6335. Min Act: -0.1700
Data Index: 7385858 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0398. Min Range: -7.0398
Max Act: 6.6335. Min Act: -0.1700
Data Index: 6969983 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19