Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 88 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.2133. Min Act: -0.1699
Data Index: 1348072 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.1508. Min Act: -0.1700
Data Index: 509230 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.1195. Min Act: -0.1700
Data Index: 1279100 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.1195. Min Act: -0.1700
Data Index: 263497 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.0570. Min Act: -0.1700
Data Index: 461165 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.0570. Min Act: -0.1700
Data Index: 760732 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2133. Min Range: -4.2133
Max Act: 4.0101. Min Act: -0.1700
Data Index: 957557 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9945. Min Act: -0.1700
Data Index: 1241379 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.8850. Min Act: -0.1700
Data Index: 29280 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9632. Min Act: -0.1700
Data Index: 662986 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9163. Min Act: -0.1700
Data Index: 597187 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9476. Min Act: -0.1700
Data Index: 114223 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9319. Min Act: -0.1700
Data Index: 700004 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9476. Min Act: -0.1700
Data Index: 614954 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9007. Min Act: -0.1700
Data Index: 3026 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.8850. Min Act: -0.1700
Data Index: 851778 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9319. Min Act: -0.1700
Data Index: 312705 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.9163. Min Act: -0.1700
Data Index: 1176485 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.8850. Min Act: -0.1700
Data Index: 208050 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2133. Min Range: -4.2133
Max Act: 3.8850. Min Act: -0.1700
Data Index: 818524 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19