Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2036 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.0408. Min Range: -4.0408
Max Act: 4.0095. Min Act: -0.1700
Data Index: 224588 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.9783. Min Act: -0.1700
Data Index: 1273455 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0408. Min Range: -4.0408
Max Act: 4.0408. Min Act: -0.1700
Data Index: 695789 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.9783. Min Act: -0.1700
Data Index: 468003 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0408. Min Range: -4.0408
Max Act: 4.0095. Min Act: -0.1700
Data Index: 1185867 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.9783. Min Act: -0.1700
Data Index: 405227 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.9470. Min Act: -0.1700
Data Index: 885026 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.9157. Min Act: -0.1700
Data Index: 785375 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8532. Min Act: -0.1700
Data Index: 672127 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.9157. Min Act: -0.1700
Data Index: 702651 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1110199 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8219. Min Act: -0.1700
Data Index: 172122 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8219. Min Act: -0.1700
Data Index: 391139 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8219. Min Act: -0.1700
Data Index: 435186 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8845. Min Act: -0.1700
Data Index: 1207261 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8219. Min Act: -0.1700
Data Index: 132554 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8219. Min Act: -0.1700
Data Index: 453576 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.7906. Min Act: -0.1700
Data Index: 1121538 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.7906. Min Act: -0.1700
Data Index: 165475 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0408. Min Range: -4.0408
Max Act: 3.8219. Min Act: -0.1700
Data Index: 354409 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19