Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 115 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7602. Min Act: -0.1700
Data Index: 199024 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7762. Min Act: -0.1700
Data Index: 1066680 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7602. Min Act: -0.1700
Data Index: 402288 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7283. Min Act: -0.1700
Data Index: 992879 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7283. Min Act: -0.1700
Data Index: 937530 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7283. Min Act: -0.1700
Data Index: 96994 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7283. Min Act: -0.1700
Data Index: 595992 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7283. Min Act: -0.1700
Data Index: 507777 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7123. Min Act: -0.1700
Data Index: 288527 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7123. Min Act: -0.1700
Data Index: 746229 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7123. Min Act: -0.1700
Data Index: 598508 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.6963. Min Act: -0.1700
Data Index: 1092110 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7123. Min Act: -0.1700
Data Index: 388187 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7123. Min Act: -0.1700
Data Index: 328281 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.7123. Min Act: -0.1700
Data Index: 1189762 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.6803. Min Act: -0.1700
Data Index: 195338 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.6803. Min Act: -0.1700
Data Index: 1107130 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.6803. Min Act: -0.1700
Data Index: 92246 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.6643. Min Act: -0.1700
Data Index: 2700 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7762. Min Range: -2.7762
Max Act: 2.6803. Min Act: -0.1700
Data Index: 374996 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19