Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0231. Min Range: -8.0231
Max Act: 8.0231. Min Act: -0.1700
Data Index: 6428099 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.8356. Min Act: -0.1700
Data Index: 92830 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.8043. Min Act: -0.1700
Data Index: 3248659 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.6793. Min Act: -0.1700
Data Index: 1611901 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.6793. Min Act: -0.1700
Data Index: 1073894 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.6168. Min Act: -0.1700
Data Index: 5529685 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.6168. Min Act: -0.1700
Data Index: 7780974 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.5856. Min Act: -0.1700
Data Index: 4665775 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.5856. Min Act: -0.1700
Data Index: 7314373 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.5543. Min Act: -0.1700
Data Index: 1418715 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.5543. Min Act: -0.1700
Data Index: 6494932 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.5231. Min Act: -0.1700
Data Index: 4985275 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.4918. Min Act: -0.1700
Data Index: 4653693 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.4606. Min Act: -0.1700
Data Index: 4032496 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.4606. Min Act: -0.1700
Data Index: 5917666 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.4606. Min Act: -0.1700
Data Index: 3003820 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.3981. Min Act: -0.1700
Data Index: 5248822 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.3356. Min Act: -0.1700
Data Index: 3119697 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.3043. Min Act: -0.1700
Data Index: 7778269 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0231. Min Range: -8.0231
Max Act: 7.2731. Min Act: -0.1700
Data Index: 4180683 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19