Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 515 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.9157. Min Act: -0.1700
Data Index: 348682 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.8844. Min Act: -0.1700
Data Index: 455067 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.8532. Min Act: -0.1700
Data Index: 1175148 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.8219. Min Act: -0.1700
Data Index: 423777 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.8063. Min Act: -0.1699
Data Index: 1194608 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1354880 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7907. Min Act: -0.1700
Data Index: 1093794 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7594. Min Act: -0.1700
Data Index: 868225 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7907. Min Act: -0.1700
Data Index: 891331 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7907. Min Act: -0.1700
Data Index: 1276397 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7438. Min Act: -0.1700
Data Index: 980784 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7438. Min Act: -0.1699
Data Index: 541721 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7438. Min Act: -0.1700
Data Index: 888457 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7282. Min Act: -0.1697
Data Index: 286991 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7438. Min Act: -0.1700
Data Index: 1122428 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7125. Min Act: -0.1700
Data Index: 397324 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7282. Min Act: -0.1700
Data Index: 295932 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7125. Min Act: -0.1700
Data Index: 395385 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7125. Min Act: -0.1700
Data Index: 1106293 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9157. Min Range: -4.9157
Max Act: 4.7125. Min Act: -0.1700
Data Index: 357488 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19