Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 43 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.2036. Min Act: -0.1700
Data Index: 1126696 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1411. Min Act: -0.1700
Data Index: 995610 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1411. Min Act: -0.1700
Data Index: 1102392 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1098. Min Act: -0.1700
Data Index: 371207 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1098. Min Act: -0.1700
Data Index: 1199684 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0786. Min Act: -0.1700
Data Index: 306705 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1098. Min Act: -0.1700
Data Index: 981372 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1098. Min Act: -0.1700
Data Index: 87092 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.1098. Min Act: -0.1700
Data Index: 842374 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0786. Min Act: -0.1700
Data Index: 1468455 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0786. Min Act: -0.1700
Data Index: 315226 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0786. Min Act: -0.1700
Data Index: 572498 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0473. Min Act: -0.1700
Data Index: 1042924 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0473. Min Act: -0.1700
Data Index: 1206536 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0473. Min Act: -0.1700
Data Index: 505271 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0473. Min Act: -0.1700
Data Index: 889373 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0786. Min Act: -0.1700
Data Index: 909988 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0473. Min Act: -0.1700
Data Index: 25240 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0473. Min Act: -0.1700
Data Index: 901601 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2036. Min Range: -4.2036
Max Act: 4.0161. Min Act: -0.1700
Data Index: 971863 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19