Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 196 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.5350. Min Act: -0.1700
Data Index: 996902 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.5189. Min Act: -0.1700
Data Index: 583847 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 1052004 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4865. Min Act: -0.1700
Data Index: 750868 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.5027. Min Act: -0.1700
Data Index: 1211552 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 1271226 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4865. Min Act: -0.1700
Data Index: 955303 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 464726 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4540. Min Act: -0.1700
Data Index: 790561 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 1340017 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4378. Min Act: -0.1700
Data Index: 270764 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4540. Min Act: -0.1700
Data Index: 619446 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 966007 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 161123 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 1082756 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4378. Min Act: -0.1700
Data Index: 520995 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4378. Min Act: -0.1700
Data Index: 835271 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4378. Min Act: -0.1700
Data Index: 245880 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4540. Min Act: -0.1700
Data Index: 635491 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5350. Min Range: -2.5350
Max Act: 2.4703. Min Act: -0.1700
Data Index: 637304 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19