Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2045 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.6962. Min Act: -0.1700
Data Index: 1139778 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.6336. Min Act: -0.1700
Data Index: 769559 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.6023. Min Act: -0.1700
Data Index: 820115 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4927. Min Act: -0.1700
Data Index: 356990 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4456. Min Act: -0.1700
Data Index: 1291573 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4613. Min Act: -0.1700
Data Index: 1052748 (C4 (Web Text))
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4456. Min Act: -0.1700
Data Index: 415740 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4300. Min Act: -0.1700
Data Index: 399092 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4143. Min Act: -0.1700
Data Index: 605123 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4143. Min Act: -0.1700
Data Index: 540291 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4456. Min Act: -0.1700
Data Index: 914090 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3986. Min Act: -0.1700
Data Index: 1131634 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4143. Min Act: -0.1700
Data Index: 189412 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3986. Min Act: -0.1700
Data Index: 1032711 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3986. Min Act: -0.1700
Data Index: 430124 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.4300. Min Act: -0.1700
Data Index: 985807 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3515. Min Act: -0.1700
Data Index: 780446 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3672. Min Act: -0.1700
Data Index: 780932 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3515. Min Act: -0.1700
Data Index: 279874 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6962. Min Range: -3.6962
Max Act: 3.3201. Min Act: -0.1700
Data Index: 312379 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19