Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1657 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8372. Min Act: -0.1700
Data Index: 818523 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8213. Min Act: -0.1700
Data Index: 949210 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8372. Min Act: -0.1700
Data Index: 696701 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8372. Min Act: -0.1700
Data Index: 1188975 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8372. Min Act: -0.1700
Data Index: 1261972 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8213. Min Act: -0.1700
Data Index: 1188621 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8213. Min Act: -0.1700
Data Index: 452928 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8054. Min Act: -0.1700
Data Index: 1173230 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8054. Min Act: -0.1700
Data Index: 340798 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8054. Min Act: -0.1700
Data Index: 447198 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7894. Min Act: -0.1700
Data Index: 1331988 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7894. Min Act: -0.1700
Data Index: 759703 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.8054. Min Act: -0.1700
Data Index: 1170977 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7735. Min Act: -0.1700
Data Index: 152837 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7894. Min Act: -0.1700
Data Index: 430525 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7894. Min Act: -0.1700
Data Index: 549590 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7735. Min Act: -0.1700
Data Index: 618871 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7735. Min Act: -0.1700
Data Index: 195113 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7894. Min Act: -0.1700
Data Index: 931551 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8372. Min Range: -2.8372
Max Act: 2.7575. Min Act: -0.1700
Data Index: 220122 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19