Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2031 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.5063. Min Act: -0.1700
Data Index: 1078841 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4750. Min Act: -0.1700
Data Index: 549121 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4438. Min Act: -0.1700
Data Index: 916134 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4438. Min Act: -0.1700
Data Index: 114149 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4438. Min Act: -0.1700
Data Index: 510642 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4125. Min Act: -0.1700
Data Index: 594918 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4125. Min Act: -0.1700
Data Index: 1019344 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4125. Min Act: -0.1700
Data Index: 1346544 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3813. Min Act: -0.1700
Data Index: 772202 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3500. Min Act: -0.1700
Data Index: 1321416 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3500. Min Act: -0.1699
Data Index: 570295 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3813. Min Act: -0.1700
Data Index: 1005476 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3813. Min Act: -0.1700
Data Index: 139121 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3188. Min Act: -0.1700
Data Index: 1021100 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3813. Min Act: -0.1700
Data Index: 1118966 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3813. Min Act: -0.1700
Data Index: 1283259 (C4 (Web Text))
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.4125. Min Act: -0.1700
Data Index: 951770 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3500. Min Act: -0.1700
Data Index: 331297 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3500. Min Act: -0.1700
Data Index: 292951 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5063. Min Range: -4.5063
Max Act: 4.3500. Min Act: -0.1700
Data Index: 514233 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19