Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 10 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.8052. Min Act: -0.1700
Data Index: 66193 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7739. Min Act: -0.1700
Data Index: 1260910 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7426. Min Act: -0.1700
Data Index: 641567 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7739. Min Act: -0.1700
Data Index: 1276902 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7426. Min Act: -0.1700
Data Index: 543507 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7426. Min Act: -0.1700
Data Index: 476437 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 175064 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7426. Min Act: -0.1700
Data Index: 918670 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 141274 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 452288 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 695063 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 1099425 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 63264 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.7113. Min Act: -0.1700
Data Index: 125800 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.6174. Min Act: -0.1700
Data Index: 960409 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.6800. Min Act: -0.1700
Data Index: 603382 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.6800. Min Act: -0.1700
Data Index: 702855 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.6487. Min Act: -0.1700
Data Index: 891712 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.6174. Min Act: -0.1700
Data Index: 40958 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8052. Min Range: -3.8052
Max Act: 3.6487. Min Act: -0.1700
Data Index: 473816 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19