Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 455 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1622. Min Range: -3.1622
Max Act: 3.1622. Min Act: -0.1700
Data Index: 1442100 (Python Code)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1622. Min Range: -3.1622
Max Act: 3.1622. Min Act: -0.1700
Data Index: 477639 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1622. Min Range: -3.1622
Max Act: 3.0992. Min Act: -0.1700
Data Index: 1579483 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1622. Min Range: -3.1622
Max Act: 3.0519. Min Act: -0.1700
Data Index: 1118658 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9887. Min Act: -0.1700
Data Index: 728686 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1622. Min Range: -3.1622
Max Act: 3.0045. Min Act: -0.1700
Data Index: 563861 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9412. Min Act: -0.1700
Data Index: 265111 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9253. Min Act: -0.1700
Data Index: 361273 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9412. Min Act: -0.1700
Data Index: 618351 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9570. Min Act: -0.1700
Data Index: 517640 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9253. Min Act: -0.1700
Data Index: 651166 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9253. Min Act: -0.1700
Data Index: 155972 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9253. Min Act: -0.1700
Data Index: 1076817 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9253. Min Act: -0.1700
Data Index: 1202691 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9095. Min Act: -0.1700
Data Index: 1047054 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9095. Min Act: -0.1700
Data Index: 627904 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9095. Min Act: -0.1700
Data Index: 1056315 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9095. Min Act: -0.1700
Data Index: 1331728 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.9253. Min Act: -0.1700
Data Index: 1285101 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1622. Min Range: -3.1622
Max Act: 2.8936. Min Act: -0.1700
Data Index: 466853 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19