Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1875 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.2282. Min Act: -0.1700
Data Index: 201537 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.2124. Min Act: -0.1700
Data Index: 24308 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.2124. Min Act: -0.1700
Data Index: 1425258 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.2124. Min Act: -0.1700
Data Index: 78021 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.2124. Min Act: -0.1700
Data Index: 310426 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 244623 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 333486 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.2124. Min Act: -0.1700
Data Index: 1355075 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 238993 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1810. Min Act: -0.1700
Data Index: 320272 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1652. Min Act: -0.1700
Data Index: 1323612 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 487845 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 1296789 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1652. Min Act: -0.1700
Data Index: 375711 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 1201029 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1652. Min Act: -0.1700
Data Index: 996244 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1967. Min Act: -0.1700
Data Index: 725598 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1652. Min Act: -0.1700
Data Index: 521086 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1495. Min Act: -0.1700
Data Index: 14474 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2282. Min Range: -3.2282
Max Act: 3.1337. Min Act: -0.1700
Data Index: 443675 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19