Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2010 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6838. Min Act: -0.1700
Data Index: 278004 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6518. Min Act: -0.1700
Data Index: 708240 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6357. Min Act: -0.1700
Data Index: 62983 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6357. Min Act: -0.1700
Data Index: 45449 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6357. Min Act: -0.1700
Data Index: 1207207 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6357. Min Act: -0.1700
Data Index: 6188 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 551615 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6036. Min Act: -0.1700
Data Index: 405389 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 528765 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 1091840 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 786837 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 1217730 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6036. Min Act: -0.1700
Data Index: 557781 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 572173 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6197. Min Act: -0.1700
Data Index: 648945 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6036. Min Act: -0.1700
Data Index: 166840 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6036. Min Act: -0.1700
Data Index: 47664 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6036. Min Act: -0.1700
Data Index: 527312 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.6036. Min Act: -0.1700
Data Index: 306655 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6838. Min Range: -2.6838
Max Act: 2.5875. Min Act: -0.1700
Data Index: 1028486 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19