Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 58 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.5484. Min Act: -0.1700
Data Index: 804206 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.4024. Min Act: -0.1700
Data Index: 1077879 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3370. Min Act: -0.1700
Data Index: 1231037 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3206. Min Act: -0.1700
Data Index: 842121 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3206. Min Act: -0.1700
Data Index: 803585 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3206. Min Act: -0.1700
Data Index: 1110045 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3206. Min Act: -0.1700
Data Index: 635671 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3041. Min Act: -0.1700
Data Index: 453388 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3041. Min Act: -0.1700
Data Index: 1312106 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3041. Min Act: -0.1700
Data Index: 184895 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.3041. Min Act: -0.1700
Data Index: 769445 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2712. Min Act: -0.1700
Data Index: 1523387 (Python Code)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2877. Min Act: -0.1700
Data Index: 304976 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2877. Min Act: -0.1700
Data Index: 521261 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2877. Min Act: -0.1700
Data Index: 441273 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2877. Min Act: -0.1700
Data Index: 983340 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2877. Min Act: -0.1700
Data Index: 1283204 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2547. Min Act: -0.1700
Data Index: 1161385 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2712. Min Act: -0.1700
Data Index: 400139 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5484. Min Range: -2.5484
Max Act: 2.2712. Min Act: -0.1700
Data Index: 923429 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19