Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1125 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.2644. Min Range: -5.2644
Max Act: 5.2644. Min Act: -0.1700
Data Index: 1334818 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2644. Min Range: -5.2644
Max Act: 5.0144. Min Act: -0.1700
Data Index: 1009359 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.8582. Min Act: -0.1700
Data Index: 1147495 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.6082. Min Act: -0.1700
Data Index: 690871 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.5144. Min Act: -0.1700
Data Index: 1083699 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.5144. Min Act: -0.1700
Data Index: 496242 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4988. Min Act: -0.1700
Data Index: 974496 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4519. Min Act: -0.1700
Data Index: 235264 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4988. Min Act: -0.1700
Data Index: 616756 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4363. Min Act: -0.1700
Data Index: 400601 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4363. Min Act: -0.1700
Data Index: 25148 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.5144. Min Act: -0.1700
Data Index: 780429 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.3738. Min Act: -0.1700
Data Index: 879912 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4050. Min Act: -0.1700
Data Index: 32908 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.3894. Min Act: -0.1700
Data Index: 457165 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4050. Min Act: -0.1700
Data Index: 111055 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.3582. Min Act: -0.1700
Data Index: 1316491 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4363. Min Act: -0.1700
Data Index: 942726 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.4050. Min Act: -0.1700
Data Index: 141236 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2644. Min Range: -5.2644
Max Act: 4.3894. Min Act: -0.1700
Data Index: 853828 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19