Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 160 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.6974. Min Act: -0.1700
Data Index: 487236 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.6654. Min Act: -0.1700
Data Index: 753148 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5850. Min Act: -0.1700
Data Index: 1573811 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5850. Min Act: -0.1700
Data Index: 84387 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5689. Min Act: -0.1700
Data Index: 24558 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5689. Min Act: -0.1700
Data Index: 1389081 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5689. Min Act: -0.1700
Data Index: 298730 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5689. Min Act: -0.1700
Data Index: 384626 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5528. Min Act: -0.1700
Data Index: 1171814 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5205. Min Act: -0.1700
Data Index: 763319 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5367. Min Act: -0.1700
Data Index: 332495 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5367. Min Act: -0.1700
Data Index: 1239927 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5367. Min Act: -0.1700
Data Index: 634181 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5367. Min Act: -0.1700
Data Index: 1075973 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5367. Min Act: -0.1700
Data Index: 1286829 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5367. Min Act: -0.1700
Data Index: 1370088 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5205. Min Act: -0.1700
Data Index: 1440218 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5205. Min Act: -0.1700
Data Index: 1626293 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5205. Min Act: -0.1700
Data Index: 1627353 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6974. Min Range: -2.6974
Max Act: 2.5205. Min Act: -0.1700
Data Index: 556825 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19