Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 920 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4668. Min Act: -0.1700
Data Index: 527426 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4506. Min Act: -0.1700
Data Index: 481206 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4506. Min Act: -0.1699
Data Index: 384230 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4017. Min Act: -0.1700
Data Index: 768276 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4180. Min Act: -0.1700
Data Index: 716199 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4180. Min Act: -0.1700
Data Index: 888014 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.4017. Min Act: -0.1700
Data Index: 610039 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3854. Min Act: -0.1700
Data Index: 604461 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3854. Min Act: -0.1700
Data Index: 942572 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3854. Min Act: -0.1700
Data Index: 1086289 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3854. Min Act: -0.1700
Data Index: 1186670 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3691. Min Act: -0.1700
Data Index: 1009532 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3691. Min Act: -0.1700
Data Index: 1106214 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3527. Min Act: -0.1700
Data Index: 676452 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3691. Min Act: -0.1700
Data Index: 889396 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3527. Min Act: -0.1700
Data Index: 895132 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3363. Min Act: -0.1700
Data Index: 468943 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3527. Min Act: -0.1700
Data Index: 582943 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3363. Min Act: -0.1700
Data Index: 1060900 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4668. Min Range: -2.4668
Max Act: 2.3363. Min Act: -0.1700
Data Index: 536123 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19