Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 57 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.3540. Min Act: -0.1700
Data Index: 178426 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.3853. Min Act: -0.1700
Data Index: 791470 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.2915. Min Act: -0.1700
Data Index: 969515 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.2290. Min Act: -0.1699
Data Index: 305745 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.2290. Min Act: -0.1699
Data Index: 475989 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.2603. Min Act: -0.1700
Data Index: 412827 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1665. Min Act: -0.1700
Data Index: 1499763 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1978. Min Act: -0.1700
Data Index: 452594 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1978. Min Act: -0.1700
Data Index: 887431 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.2290. Min Act: -0.1700
Data Index: 107837 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1978. Min Act: -0.1700
Data Index: 233966 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1665. Min Act: -0.1700
Data Index: 242492 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1665. Min Act: -0.1700
Data Index: 379735 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1665. Min Act: -0.1700
Data Index: 511408 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1352. Min Act: -0.1700
Data Index: 583645 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1352. Min Act: -0.1700
Data Index: 194168 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1352. Min Act: -0.1700
Data Index: 1595545 (Python Code)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1352. Min Act: -0.1700
Data Index: 985191 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1352. Min Act: -0.1700
Data Index: 160392 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3853. Min Range: -4.3853
Max Act: 4.1040. Min Act: -0.1700
Data Index: 1108387 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19