Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1992 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0763. Min Act: -0.1700
Data Index: 243354 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0605. Min Act: -0.1700
Data Index: 1306256 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0289. Min Act: -0.1700
Data Index: 37651 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0289. Min Act: -0.1700
Data Index: 773496 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0289. Min Act: -0.1700
Data Index: 1288970 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0131. Min Act: -0.1700
Data Index: 723897 (C4 (Web Text))
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0131. Min Act: -0.1700
Data Index: 1010393 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0131. Min Act: -0.1700
Data Index: 1264105 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0763. Min Range: -3.0763
Max Act: 3.0131. Min Act: -0.1700
Data Index: 869172 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9973. Min Act: -0.1700
Data Index: 537116 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9815. Min Act: -0.1700
Data Index: 895766 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9973. Min Act: -0.1700
Data Index: 935765 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9657. Min Act: -0.1700
Data Index: 215148 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9973. Min Act: -0.1700
Data Index: 45382 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9815. Min Act: -0.1700
Data Index: 1123086 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9815. Min Act: -0.1700
Data Index: 1229288 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9815. Min Act: -0.1700
Data Index: 533954 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9815. Min Act: -0.1700
Data Index: 308296 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9498. Min Act: -0.1700
Data Index: 28183 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0763. Min Range: -3.0763
Max Act: 2.9815. Min Act: -0.1700
Data Index: 123171 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19