Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2027 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.1670. Min Act: -0.1700
Data Index: 12175 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.1670. Min Act: -0.1700
Data Index: 450296 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.1337. Min Act: -0.1700
Data Index: 235777 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.1003. Min Act: -0.1699
Data Index: 1139753 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.1003. Min Act: -0.1700
Data Index: 1149024 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0835. Min Act: -0.1700
Data Index: 969449 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0668. Min Act: -0.1700
Data Index: 147634 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0668. Min Act: -0.1698
Data Index: 656974 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0500. Min Act: -0.1700
Data Index: 459848 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0668. Min Act: -0.1696
Data Index: 1105288 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0500. Min Act: -0.1700
Data Index: 248545 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0331. Min Act: -0.1700
Data Index: 213939 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0500. Min Act: -0.1699
Data Index: 937083 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0331. Min Act: -0.1700
Data Index: 187346 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0500. Min Act: -0.1700
Data Index: 1110953 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0331. Min Act: -0.1700
Data Index: 437684 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0331. Min Act: -0.1699
Data Index: 1087056 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0500. Min Act: -0.1700
Data Index: 483539 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0331. Min Act: -0.1700
Data Index: 403685 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1670. Min Range: -2.1670
Max Act: 2.0500. Min Act: -0.1700
Data Index: 97889 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19