Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1824 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.0632. Min Range: -3.0632
Max Act: 3.0632. Min Act: -0.1700
Data Index: 479398 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0632. Min Range: -3.0632
Max Act: 3.0000. Min Act: -0.1700
Data Index: 189246 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0632. Min Range: -3.0632
Max Act: 3.0000. Min Act: -0.1700
Data Index: 1249632 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9842. Min Act: -0.1700
Data Index: 919223 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9684. Min Act: -0.1700
Data Index: 338923 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9684. Min Act: -0.1700
Data Index: 115936 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9684. Min Act: -0.1700
Data Index: 148336 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9684. Min Act: -0.1700
Data Index: 615460 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9367. Min Act: -0.1700
Data Index: 1107751 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9208. Min Act: -0.1700
Data Index: 555955 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9050. Min Act: -0.1700
Data Index: 867871 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9208. Min Act: -0.1700
Data Index: 355885 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9208. Min Act: -0.1700
Data Index: 564589 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9208. Min Act: -0.1700
Data Index: 1101708 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9367. Min Act: -0.1700
Data Index: 595202 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9208. Min Act: -0.1700
Data Index: 152716 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9367. Min Act: -0.1700
Data Index: 1106638 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9050. Min Act: -0.1700
Data Index: 77170 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.8891. Min Act: -0.1700
Data Index: 644601 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0632. Min Range: -3.0632
Max Act: 2.9050. Min Act: -0.1700
Data Index: 680674 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19