Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 826 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.8302. Min Act: -0.1700
Data Index: 1351082 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7825. Min Act: -0.1700
Data Index: 741020 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7506. Min Act: -0.1700
Data Index: 439835 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7506. Min Act: -0.1700
Data Index: 9161 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7346. Min Act: -0.1700
Data Index: 337099 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7186. Min Act: -0.1700
Data Index: 1239288 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7186. Min Act: -0.1700
Data Index: 532509 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6866. Min Act: -0.1700
Data Index: 939554 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7186. Min Act: -0.1700
Data Index: 591892 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7026. Min Act: -0.1700
Data Index: 245528 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6866. Min Act: -0.1700
Data Index: 840723 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6866. Min Act: -0.1700
Data Index: 1252810 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6866. Min Act: -0.1700
Data Index: 449620 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6866. Min Act: -0.1700
Data Index: 137034 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6866. Min Act: -0.1700
Data Index: 504400 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.7026. Min Act: -0.1700
Data Index: 1036168 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6706. Min Act: -0.1700
Data Index: 1075148 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6706. Min Act: -0.1700
Data Index: 1001750 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6546. Min Act: -0.1700
Data Index: 58045 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8302. Min Range: -2.8302
Max Act: 2.6706. Min Act: -0.1700
Data Index: 1086644 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19