Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1975 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.9252. Min Act: -0.1700
Data Index: 993978 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.8458. Min Act: -0.1700
Data Index: 630755 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.8458. Min Act: -0.1700
Data Index: 772869 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7981. Min Act: -0.1700
Data Index: 587175 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.8299. Min Act: -0.1700
Data Index: 1328040 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.8140. Min Act: -0.1700
Data Index: 154294 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.8140. Min Act: -0.1700
Data Index: 47470 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7981. Min Act: -0.1700
Data Index: 505763 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7821. Min Act: -0.1700
Data Index: 1130583 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7981. Min Act: -0.1700
Data Index: 475027 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7821. Min Act: -0.1700
Data Index: 364200 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7821. Min Act: -0.1700
Data Index: 1315403 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7662. Min Act: -0.1700
Data Index: 235799 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7821. Min Act: -0.1700
Data Index: 212874 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7502. Min Act: -0.1700
Data Index: 298093 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7662. Min Act: -0.1700
Data Index: 297494 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7502. Min Act: -0.1700
Data Index: 64718 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7662. Min Act: -0.1700
Data Index: 911000 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7502. Min Act: -0.1700
Data Index: 1185411 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9252. Min Range: -2.9252
Max Act: 2.7662. Min Act: -0.1700
Data Index: 399597 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19