Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1985 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 5.2018. Min Range: -5.2018
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1324139 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2018. Min Range: -5.2018
Max Act: 5.0143. Min Act: -0.1700
Data Index: 124918 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.9831. Min Act: -0.1700
Data Index: 704355 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2018. Min Range: -5.2018
Max Act: 5.0143. Min Act: -0.1700
Data Index: 263579 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.9831. Min Act: -0.1700
Data Index: 1314859 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.9206. Min Act: -0.1700
Data Index: 449498 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8893. Min Act: -0.1700
Data Index: 414019 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.9206. Min Act: -0.1700
Data Index: 143577 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8893. Min Act: -0.1700
Data Index: 781498 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8581. Min Act: -0.1700
Data Index: 209592 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8581. Min Act: -0.1700
Data Index: 360055 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8581. Min Act: -0.1700
Data Index: 807558 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8268. Min Act: -0.1700
Data Index: 248561 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.7956. Min Act: -0.1700
Data Index: 260077 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8581. Min Act: -0.1700
Data Index: 152393 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8268. Min Act: -0.1700
Data Index: 1155306 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8268. Min Act: -0.1700
Data Index: 1043521 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.8268. Min Act: -0.1700
Data Index: 1041224 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.7643. Min Act: -0.1700
Data Index: 155110 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2018. Min Range: -5.2018
Max Act: 4.7956. Min Act: -0.1700
Data Index: 979116 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19