Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1088 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.6347. Min Act: -0.1700
Data Index: 196297 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.5410. Min Act: -0.1700
Data Index: 1277349 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.5722. Min Act: -0.1700
Data Index: 530802 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.5722. Min Act: -0.1700
Data Index: 156375 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.5410. Min Act: -0.1700
Data Index: 1206932 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.5097. Min Act: -0.1700
Data Index: 1059610 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.4785. Min Act: -0.1700
Data Index: 855555 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.4785. Min Act: -0.1700
Data Index: 652115 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.4472. Min Act: -0.1700
Data Index: 667137 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.4160. Min Act: -0.1700
Data Index: 467600 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.4160. Min Act: -0.1700
Data Index: 1275713 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3847. Min Act: -0.1700
Data Index: 628900 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3847. Min Act: -0.1700
Data Index: 27647 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3535. Min Act: -0.1700
Data Index: 30769 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3847. Min Act: -0.1700
Data Index: 329636 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3847. Min Act: -0.1700
Data Index: 924651 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3535. Min Act: -0.1700
Data Index: 170706 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3222. Min Act: -0.1700
Data Index: 1000563 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3222. Min Act: -0.1700
Data Index: 1126930 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6347. Min Range: -4.6347
Max Act: 4.3222. Min Act: -0.1700
Data Index: 11650 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19