Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 452 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0347. Min Range: -5.0347
Max Act: 5.0347. Min Act: -0.1700
Data Index: 4465748 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.9410. Min Act: -0.1700
Data Index: 1103825 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7847. Min Act: -0.1700
Data Index: 2183905 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7847. Min Act: -0.1700
Data Index: 4302675 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7535. Min Act: -0.1700
Data Index: 5278952 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7222. Min Act: -0.1700
Data Index: 6379639 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7222. Min Act: -0.1700
Data Index: 8257360 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7222. Min Act: -0.1700
Data Index: 1379790 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6910. Min Act: -0.1700
Data Index: 1853217 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.7222. Min Act: -0.1700
Data Index: 2428174 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6910. Min Act: -0.1700
Data Index: 8046806 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6910. Min Act: -0.1700
Data Index: 5199154 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 8062550 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6910. Min Act: -0.1700
Data Index: 5636275 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 6404997 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 5934260 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 593552 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 8488126 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 6504614 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0347. Min Range: -5.0347
Max Act: 4.6597. Min Act: -0.1700
Data Index: 7361415 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19