Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 201 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.9345. Min Act: -0.1700
Data Index: 274851 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8711. Min Act: -0.1700
Data Index: 133937 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8870. Min Act: -0.1700
Data Index: 1116829 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8711. Min Act: -0.1700
Data Index: 165534 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8393. Min Act: -0.1700
Data Index: 705017 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8393. Min Act: -0.1700
Data Index: 417499 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8234. Min Act: -0.1700
Data Index: 605224 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8075. Min Act: -0.1700
Data Index: 1210334 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8075. Min Act: -0.1700
Data Index: 646126 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8234. Min Act: -0.1700
Data Index: 971832 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8234. Min Act: -0.1700
Data Index: 1060320 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8234. Min Act: -0.1700
Data Index: 1068178 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7916. Min Act: -0.1700
Data Index: 1325276 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7916. Min Act: -0.1700
Data Index: 621506 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7916. Min Act: -0.1700
Data Index: 395270 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7916. Min Act: -0.1700
Data Index: 931373 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.8075. Min Act: -0.1700
Data Index: 1076358 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7916. Min Act: -0.1700
Data Index: 1045104 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7916. Min Act: -0.1700
Data Index: 478776 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9345. Min Range: -2.9345
Max Act: 2.7756. Min Act: -0.1700
Data Index: 734340 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19