Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 951 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0434. Min Range: -3.0434
Max Act: 3.0434. Min Act: -0.1700
Data Index: 236461 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9643. Min Act: -0.1700
Data Index: 1340714 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9960. Min Act: -0.1700
Data Index: 1264775 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9485. Min Act: -0.1700
Data Index: 921738 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9168. Min Act: -0.1700
Data Index: 267710 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9010. Min Act: -0.1700
Data Index: 1229024 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9327. Min Act: -0.1700
Data Index: 706279 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.9010. Min Act: -0.1700
Data Index: 1138158 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8851. Min Act: -0.1700
Data Index: 1222574 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8374. Min Act: -0.1700
Data Index: 1063601 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8215. Min Act: -0.1700
Data Index: 121263 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8374. Min Act: -0.1700
Data Index: 13493 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8533. Min Act: -0.1700
Data Index: 576614 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8374. Min Act: -0.1700
Data Index: 162428 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8374. Min Act: -0.1700
Data Index: 1033290 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8215. Min Act: -0.1700
Data Index: 1013489 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8215. Min Act: -0.1700
Data Index: 23063 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8374. Min Act: -0.1700
Data Index: 830508 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8056. Min Act: -0.1700
Data Index: 921469 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0434. Min Range: -3.0434
Max Act: 2.8215. Min Act: -0.1700
Data Index: 567589 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19