Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1937 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5697. Min Act: -0.1700
Data Index: 484353 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 1274154 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 925854 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 1282041 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5385. Min Act: -0.1700
Data Index: 656633 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 1009506 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1700
Data Index: 59097 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4760. Min Act: -0.1700
Data Index: 285483 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 977146 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.5072. Min Act: -0.1699
Data Index: 66270 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 547358 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 668191 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 343878 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 666968 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 784970 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 839470 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 234212 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 438387 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4135. Min Act: -0.1700
Data Index: 1107987 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5697. Min Range: -4.5697
Max Act: 4.4447. Min Act: -0.1700
Data Index: 1168141 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19