Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 483 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.9312. Min Act: -0.1700
Data Index: 798718 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.8374. Min Act: -0.1700
Data Index: 615937 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.7749. Min Act: -0.1700
Data Index: 638292 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.6187. Min Act: -0.1700
Data Index: 1166689 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.5562. Min Act: -0.1700
Data Index: 153079 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.5562. Min Act: -0.1700
Data Index: 562374 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.4937. Min Act: -0.1700
Data Index: 675791 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.4937. Min Act: -0.1700
Data Index: 671955 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.4312. Min Act: -0.1700
Data Index: 431578 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.4937. Min Act: -0.1700
Data Index: 866681 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.5249. Min Act: -0.1700
Data Index: 844935 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.5249. Min Act: -0.1700
Data Index: 1209178 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.4937. Min Act: -0.1700
Data Index: 242534 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.4312. Min Act: -0.1700
Data Index: 147086 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.3999. Min Act: -0.1700
Data Index: 514155 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.3999. Min Act: -0.1700
Data Index: 248673 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.3687. Min Act: -0.1700
Data Index: 832656 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.3061. Min Act: -0.1700
Data Index: 1200120 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.3687. Min Act: -0.1700
Data Index: 361083 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9312. Min Range: -4.9312
Max Act: 4.3374. Min Act: -0.1700
Data Index: 510837 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19