Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 683 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.5255. Min Act: -0.1700
Data Index: 262325 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.4445. Min Act: -0.1700
Data Index: 219135 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.4445. Min Act: -0.1700
Data Index: 1287225 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.4282. Min Act: -0.1700
Data Index: 372275 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.4119. Min Act: -0.1700
Data Index: 131601 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3629. Min Act: -0.1700
Data Index: 335677 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3629. Min Act: -0.1700
Data Index: 63570 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3629. Min Act: -0.1700
Data Index: 375073 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3629. Min Act: -0.1700
Data Index: 790883 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3302. Min Act: -0.1700
Data Index: 1589090 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3138. Min Act: -0.1700
Data Index: 1263229 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3138. Min Act: -0.1700
Data Index: 774981 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3138. Min Act: -0.1700
Data Index: 115587 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3138. Min Act: -0.1700
Data Index: 262102 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3138. Min Act: -0.1700
Data Index: 1275661 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.3138. Min Act: -0.1700
Data Index: 1252759 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.2809. Min Act: -0.1699
Data Index: 629456 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.2973. Min Act: -0.1700
Data Index: 402376 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.2809. Min Act: -0.1700
Data Index: 98530 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5255. Min Range: -2.5255
Max Act: 2.2809. Min Act: -0.1700
Data Index: 1187419 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19