Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1878 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.5832. Min Act: -0.1700
Data Index: 862386 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.5348. Min Act: -0.1700
Data Index: 220004 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.5187. Min Act: -0.1700
Data Index: 1215632 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.5025. Min Act: -0.1700
Data Index: 2098 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4863. Min Act: -0.1700
Data Index: 298211 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.5025. Min Act: -0.1700
Data Index: 859160 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4701. Min Act: -0.1700
Data Index: 1170320 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4701. Min Act: -0.1700
Data Index: 347106 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4701. Min Act: -0.1700
Data Index: 62496 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4701. Min Act: -0.1700
Data Index: 228973 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4863. Min Act: -0.1700
Data Index: 1172401 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4538. Min Act: -0.1700
Data Index: 1112644 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4701. Min Act: -0.1700
Data Index: 882662 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4701. Min Act: -0.1700
Data Index: 50071 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4376. Min Act: -0.1700
Data Index: 796587 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4376. Min Act: -0.1700
Data Index: 783435 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4376. Min Act: -0.1700
Data Index: 1248998 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4376. Min Act: -0.1700
Data Index: 1335715 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4376. Min Act: -0.1700
Data Index: 221593 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5832. Min Range: -2.5832
Max Act: 2.4213. Min Act: -0.1700
Data Index: 299021 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19