Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 134 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.9181. Min Act: -0.1700
Data Index: 535750 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8712. Min Act: -0.1700
Data Index: 502475 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8243. Min Act: -0.1700
Data Index: 1196926 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 793299 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 584947 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 1151538 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 1247116 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7930. Min Act: -0.1700
Data Index: 709736 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 94663 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 276596 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.8086. Min Act: -0.1700
Data Index: 1111251 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7773. Min Act: -0.1700
Data Index: 663717 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7773. Min Act: -0.1700
Data Index: 942457 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7930. Min Act: -0.1700
Data Index: 606619 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7617. Min Act: -0.1700
Data Index: 874635 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7930. Min Act: -0.1700
Data Index: 1291572 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7773. Min Act: -0.1700
Data Index: 1230268 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7930. Min Act: -0.1700
Data Index: 277681 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7930. Min Act: -0.1700
Data Index: 227925 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9181. Min Range: -3.9181
Max Act: 3.7617. Min Act: -0.1700
Data Index: 41277 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19