Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 82 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.7606. Min Act: -0.1700
Data Index: 1255933 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.5105. Min Act: -0.1700
Data Index: 1078103 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.5418. Min Act: -0.1700
Data Index: 757792 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.5105. Min Act: -0.1700
Data Index: 487072 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.5418. Min Act: -0.1700
Data Index: 224678 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4793. Min Act: -0.1700
Data Index: 538932 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.5105. Min Act: -0.1700
Data Index: 317800 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4793. Min Act: -0.1700
Data Index: 43933 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4480. Min Act: -0.1700
Data Index: 631533 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4168. Min Act: -0.1700
Data Index: 416418 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3855. Min Act: -0.1700
Data Index: 1145985 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4168. Min Act: -0.1700
Data Index: 526274 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4168. Min Act: -0.1700
Data Index: 975214 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3543. Min Act: -0.1700
Data Index: 451024 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3855. Min Act: -0.1700
Data Index: 592615 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.4168. Min Act: -0.1700
Data Index: 129771 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3543. Min Act: -0.1700
Data Index: 1016009 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3230. Min Act: -0.1700
Data Index: 293371 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3230. Min Act: -0.1700
Data Index: 1192745 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7606. Min Range: -4.7606
Max Act: 4.3230. Min Act: -0.1700
Data Index: 745399 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19