Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 22 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.1033. Min Act: -0.1700
Data Index: 1357291 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.0408. Min Act: -0.1700
Data Index: 261689 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.0095. Min Act: -0.1700
Data Index: 286555 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.0095. Min Act: -0.1700
Data Index: 616423 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.0095. Min Act: -0.1700
Data Index: 431360 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.0095. Min Act: -0.1700
Data Index: 51962 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1033. Min Range: -4.1033
Max Act: 4.0095. Min Act: -0.1700
Data Index: 1158599 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9783. Min Act: -0.1700
Data Index: 227429 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9157. Min Act: -0.1700
Data Index: 559895 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9157. Min Act: -0.1700
Data Index: 496232 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9157. Min Act: -0.1700
Data Index: 927877 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9157. Min Act: -0.1700
Data Index: 832140 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1042986 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9470. Min Act: -0.1700
Data Index: 1343669 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9157. Min Act: -0.1700
Data Index: 1110238 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.9157. Min Act: -0.1700
Data Index: 324408 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.8845. Min Act: -0.1700
Data Index: 530001 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1004612 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.8219. Min Act: -0.1700
Data Index: 895828 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1033. Min Range: -4.1033
Max Act: 3.8219. Min Act: -0.1700
Data Index: 216029 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19