Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 13 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.7461. Min Act: -0.1700
Data Index: 12064 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6981. Min Act: -0.1700
Data Index: 1028382 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6981. Min Act: -0.1700
Data Index: 728178 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6981. Min Act: -0.1700
Data Index: 1305437 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6821. Min Act: -0.1700
Data Index: 818554 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6981. Min Act: -0.1700
Data Index: 676963 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.7141. Min Act: -0.1700
Data Index: 559180 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 96091 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6661. Min Act: -0.1700
Data Index: 888132 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 845968 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 548988 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 226350 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6340. Min Act: -0.1700
Data Index: 314117 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6661. Min Act: -0.1700
Data Index: 971071 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 1217153 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 50819 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6340. Min Act: -0.1700
Data Index: 1083884 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6500. Min Act: -0.1700
Data Index: 956129 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6018. Min Act: -0.1700
Data Index: 352860 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7461. Min Range: -2.7461
Max Act: 2.6340. Min Act: -0.1700
Data Index: 1129700 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19