Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 67 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0141. Min Range: -4.0141
Max Act: 4.0141. Min Act: -0.1700
Data Index: 647077 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9828. Min Act: -0.1700
Data Index: 1028647 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9516. Min Act: -0.1700
Data Index: 161352 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9516. Min Act: -0.1700
Data Index: 593153 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9516. Min Act: -0.1700
Data Index: 633747 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8890. Min Act: -0.1700
Data Index: 943064 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9203. Min Act: -0.1700
Data Index: 1066792 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9516. Min Act: -0.1700
Data Index: 401448 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.9203. Min Act: -0.1700
Data Index: 874216 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8890. Min Act: -0.1700
Data Index: 818997 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8734. Min Act: -0.1700
Data Index: 333672 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8890. Min Act: -0.1700
Data Index: 578308 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8890. Min Act: -0.1700
Data Index: 835845 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8734. Min Act: -0.1700
Data Index: 544843 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8890. Min Act: -0.1700
Data Index: 813002 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8734. Min Act: -0.1700
Data Index: 636205 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8577. Min Act: -0.1700
Data Index: 165874 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8577. Min Act: -0.1700
Data Index: 787287 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8577. Min Act: -0.1700
Data Index: 296958 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0141. Min Range: -4.0141
Max Act: 3.8890. Min Act: -0.1700
Data Index: 728714 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19