Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 537 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.5286. Min Act: -0.1700
Data Index: 131830 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.4476. Min Act: -0.1700
Data Index: 201060 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.4476. Min Act: -0.1700
Data Index: 985953 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.4313. Min Act: -0.1700
Data Index: 599897 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3987. Min Act: -0.1700
Data Index: 387293 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.4150. Min Act: -0.1700
Data Index: 51518 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3987. Min Act: -0.1700
Data Index: 235583 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3824. Min Act: -0.1700
Data Index: 119102 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3661. Min Act: -0.1700
Data Index: 160236 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3661. Min Act: -0.1700
Data Index: 450839 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3661. Min Act: -0.1700
Data Index: 873331 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3661. Min Act: -0.1700
Data Index: 675979 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3661. Min Act: -0.1700
Data Index: 1174731 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3169. Min Act: -0.1700
Data Index: 975083 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3333. Min Act: -0.1700
Data Index: 1198752 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3333. Min Act: -0.1700
Data Index: 232497 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3333. Min Act: -0.1700
Data Index: 259010 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3333. Min Act: -0.1700
Data Index: 846318 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3169. Min Act: -0.1700
Data Index: 414466 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5286. Min Range: -2.5286
Max Act: 2.3005. Min Act: -0.1700
Data Index: 400651 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19