Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 129 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.2637. Min Act: -0.1700
Data Index: 608276 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.1386. Min Act: -0.1700
Data Index: 20938 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.1074. Min Act: -0.1700
Data Index: 1096105 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.1386. Min Act: -0.1700
Data Index: 468455 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0761. Min Act: -0.1700
Data Index: 1165185 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0761. Min Act: -0.1700
Data Index: 990836 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0449. Min Act: -0.1700
Data Index: 526559 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0449. Min Act: -0.1699
Data Index: 1496858 (Python Code)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.1074. Min Act: -0.1700
Data Index: 1290004 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0761. Min Act: -0.1700
Data Index: 375164 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0136. Min Act: -0.1700
Data Index: 926192 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.1386. Min Act: -0.1700
Data Index: 465085 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0449. Min Act: -0.1700
Data Index: 584727 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0136. Min Act: -0.1700
Data Index: 137756 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0136. Min Act: -0.1700
Data Index: 89192 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0136. Min Act: -0.1700
Data Index: 71212 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0136. Min Act: -0.1700
Data Index: 634574 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0136. Min Act: -0.1700
Data Index: 381605 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0449. Min Act: -0.1700
Data Index: 259585 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2637. Min Range: -4.2637
Max Act: 4.0449. Min Act: -0.1700
Data Index: 1122708 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19