Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 47 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.4852. Min Act: -0.1700
Data Index: 1297821 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.3445. Min Act: -0.1700
Data Index: 61087 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1414. Min Act: -0.1700
Data Index: 583461 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1883. Min Act: -0.1700
Data Index: 764710 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1726. Min Act: -0.1699
Data Index: 1339593 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1414. Min Act: -0.1699
Data Index: 840243 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1414. Min Act: -0.1700
Data Index: 425444 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.2039. Min Act: -0.1700
Data Index: 355408 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1257. Min Act: -0.1700
Data Index: 1249325 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1257. Min Act: -0.1700
Data Index: 135076 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0789. Min Act: -0.1700
Data Index: 983664 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0632. Min Act: -0.1700
Data Index: 1268820 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1101. Min Act: -0.1700
Data Index: 995492 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0945. Min Act: -0.1700
Data Index: 1179350 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0632. Min Act: -0.1700
Data Index: 568819 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0789. Min Act: -0.1700
Data Index: 379334 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.1257. Min Act: -0.1700
Data Index: 666360 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0632. Min Act: -0.1700
Data Index: 826974 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0476. Min Act: -0.1700
Data Index: 927791 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4852. Min Range: -4.4852
Max Act: 4.0320. Min Act: -0.1700
Data Index: 505358 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19