Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 8 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6859. Min Act: -0.1700
Data Index: 282530 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6699. Min Act: -0.1700
Data Index: 309797 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6539. Min Act: -0.1700
Data Index: 998380 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6218. Min Act: -0.1700
Data Index: 1130715 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6057. Min Act: -0.1700
Data Index: 841853 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6218. Min Act: -0.1700
Data Index: 536115 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6218. Min Act: -0.1700
Data Index: 531031 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6057. Min Act: -0.1700
Data Index: 1291200 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5896. Min Act: -0.1700
Data Index: 848011 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.6057. Min Act: -0.1700
Data Index: 1285912 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5735. Min Act: -0.1700
Data Index: 1282842 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5896. Min Act: -0.1700
Data Index: 969597 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5896. Min Act: -0.1700
Data Index: 398586 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5735. Min Act: -0.1700
Data Index: 254198 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5573. Min Act: -0.1700
Data Index: 197087 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5735. Min Act: -0.1700
Data Index: 725671 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5735. Min Act: -0.1700
Data Index: 5030 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5735. Min Act: -0.1700
Data Index: 116444 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5573. Min Act: -0.1700
Data Index: 1066904 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6859. Min Range: -2.6859
Max Act: 2.5573. Min Act: -0.1700
Data Index: 215563 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19