Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 60 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.6070. Min Act: -0.1700
Data Index: 455314 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.4195. Min Act: -0.1700
Data Index: 234659 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.3883. Min Act: -0.1700
Data Index: 880591 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.3570. Min Act: -0.1700
Data Index: 104068 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.3570. Min Act: -0.1700
Data Index: 196885 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.3258. Min Act: -0.1700
Data Index: 795096 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.3258. Min Act: -0.1700
Data Index: 353140 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2945. Min Act: -0.1700
Data Index: 809080 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2633. Min Act: -0.1700
Data Index: 1323776 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2945. Min Act: -0.1700
Data Index: 21518 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2789. Min Act: -0.1700
Data Index: 1259771 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2164. Min Act: -0.1700
Data Index: 947871 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2320. Min Act: -0.1700
Data Index: 895986 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2320. Min Act: -0.1700
Data Index: 101228 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.1695. Min Act: -0.1700
Data Index: 584675 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2164. Min Act: -0.1700
Data Index: 476840 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2164. Min Act: -0.1700
Data Index: 223634 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.1851. Min Act: -0.1700
Data Index: 998544 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.2164. Min Act: -0.1700
Data Index: 946968 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6070. Min Range: -4.6070
Max Act: 4.1539. Min Act: -0.1700
Data Index: 98030 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19