Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2038 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.5086. Min Act: -0.1700
Data Index: 798983 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.3836. Min Act: -0.1700
Data Index: 109980 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.3524. Min Act: -0.1700
Data Index: 16779 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.3524. Min Act: -0.1700
Data Index: 438208 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.2899. Min Act: -0.1700
Data Index: 663832 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.2899. Min Act: -0.1700
Data Index: 138000 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.2899. Min Act: -0.1700
Data Index: 629212 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.2274. Min Act: -0.1700
Data Index: 669074 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.2586. Min Act: -0.1700
Data Index: 99209 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.2586. Min Act: -0.1700
Data Index: 734062 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1961. Min Act: -0.1700
Data Index: 610936 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1648. Min Act: -0.1699
Data Index: 107545 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1961. Min Act: -0.1700
Data Index: 248386 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1648. Min Act: -0.1700
Data Index: 1205756 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1648. Min Act: -0.1700
Data Index: 1119726 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1648. Min Act: -0.1700
Data Index: 600941 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1648. Min Act: -0.1700
Data Index: 454220 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1336. Min Act: -0.1700
Data Index: 1141843 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.1023. Min Act: -0.1700
Data Index: 545599 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5086. Min Range: -4.5086
Max Act: 4.0711. Min Act: -0.1700
Data Index: 718163 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19