Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1939 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.4387. Min Act: -0.1700
Data Index: 1215996 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.4224. Min Act: -0.1700
Data Index: 371910 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.4061. Min Act: -0.1700
Data Index: 818932 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.4061. Min Act: -0.1700
Data Index: 1273660 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3898. Min Act: -0.1700
Data Index: 575199 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3735. Min Act: -0.1700
Data Index: 925647 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3898. Min Act: -0.1700
Data Index: 996550 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3571. Min Act: -0.1700
Data Index: 880007 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3571. Min Act: -0.1700
Data Index: 593268 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3571. Min Act: -0.1700
Data Index: 635566 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3735. Min Act: -0.1700
Data Index: 1090153 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3571. Min Act: -0.1700
Data Index: 1116527 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3407. Min Act: -0.1700
Data Index: 37178 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3407. Min Act: -0.1700
Data Index: 324353 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3407. Min Act: -0.1700
Data Index: 55300 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3079. Min Act: -0.1699
Data Index: 1119296 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3243. Min Act: -0.1700
Data Index: 670373 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3079. Min Act: -0.1700
Data Index: 290148 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3079. Min Act: -0.1700
Data Index: 1238745 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4387. Min Range: -2.4387
Max Act: 2.3079. Min Act: -0.1700
Data Index: 1069877 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19