Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1870 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4939. Min Act: -0.1700
Data Index: 418325 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 287605 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 969023 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 900831 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 734147 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 605652 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 368465 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4452. Min Act: -0.1700
Data Index: 614106 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4452. Min Act: -0.1700
Data Index: 563191 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4615. Min Act: -0.1700
Data Index: 712988 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4289. Min Act: -0.1700
Data Index: 1081084 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4289. Min Act: -0.1700
Data Index: 265992 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4289. Min Act: -0.1700
Data Index: 583376 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4289. Min Act: -0.1700
Data Index: 1128761 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4289. Min Act: -0.1700
Data Index: 336422 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.3964. Min Act: -0.1700
Data Index: 940266 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4127. Min Act: -0.1700
Data Index: 38560 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.3964. Min Act: -0.1700
Data Index: 950674 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.4127. Min Act: -0.1700
Data Index: 1030516 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4939. Min Range: -2.4939
Max Act: 2.3964. Min Act: -0.1700
Data Index: 141687 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19