Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 272 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.8627. Min Act: -0.1700
Data Index: 1161240 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.8150. Min Act: -0.1700
Data Index: 639677 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7672. Min Act: -0.1700
Data Index: 985526 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7353. Min Act: -0.1700
Data Index: 615738 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7672. Min Act: -0.1700
Data Index: 207946 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7353. Min Act: -0.1700
Data Index: 772423 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7193. Min Act: -0.1700
Data Index: 193438 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 291855 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7193. Min Act: -0.1700
Data Index: 566808 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7193. Min Act: -0.1700
Data Index: 1068008 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7193. Min Act: -0.1700
Data Index: 1181985 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.6873. Min Act: -0.1700
Data Index: 497463 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 178797 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 780399 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 1011060 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.6873. Min Act: -0.1700
Data Index: 666095 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 680904 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 1080248 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 442250 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8627. Min Range: -2.8627
Max Act: 2.7033. Min Act: -0.1700
Data Index: 733155 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19