Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 107 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.5211. Min Act: -0.1700
Data Index: 21825 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.4273. Min Act: -0.1700
Data Index: 791667 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.3648. Min Act: -0.1700
Data Index: 44244 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.3961. Min Act: -0.1700
Data Index: 1301733 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.3023. Min Act: -0.1700
Data Index: 419648 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.3336. Min Act: -0.1700
Data Index: 700499 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.3336. Min Act: -0.1700
Data Index: 251024 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2711. Min Act: -0.1700
Data Index: 598422 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2711. Min Act: -0.1700
Data Index: 227803 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2711. Min Act: -0.1700
Data Index: 339993 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2398. Min Act: -0.1700
Data Index: 16502 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2398. Min Act: -0.1700
Data Index: 692363 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.1773. Min Act: -0.1700
Data Index: 547806 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2711. Min Act: -0.1700
Data Index: 807702 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2711. Min Act: -0.1700
Data Index: 1260361 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2398. Min Act: -0.1700
Data Index: 1075969 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2711. Min Act: -0.1700
Data Index: 340636 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2398. Min Act: -0.1700
Data Index: 613068 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.1460. Min Act: -0.1700
Data Index: 948047 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5211. Min Range: -4.5211
Max Act: 4.2085. Min Act: -0.1700
Data Index: 1025304 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19