Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1870 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0474. Min Range: -4.0474
Max Act: 4.0474. Min Act: -0.1700
Data Index: 752792 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9848. Min Act: -0.1700
Data Index: 937660 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0474. Min Range: -4.0474
Max Act: 4.0161. Min Act: -0.1700
Data Index: 1013846 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9536. Min Act: -0.1700
Data Index: 319980 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9536. Min Act: -0.1700
Data Index: 367180 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9536. Min Act: -0.1700
Data Index: 587024 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9536. Min Act: -0.1700
Data Index: 299057 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9536. Min Act: -0.1700
Data Index: 934006 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 336790 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 270059 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 1017836 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 1230423 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.9223. Min Act: -0.1700
Data Index: 345439 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8597. Min Act: -0.1700
Data Index: 660922 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 486710 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 479305 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 122027 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8910. Min Act: -0.1700
Data Index: 1124102 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8597. Min Act: -0.1700
Data Index: 329320 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0474. Min Range: -4.0474
Max Act: 3.8285. Min Act: -0.1700
Data Index: 485118 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19