Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 748 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.4870. Min Act: -0.1700
Data Index: 15853 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.4245. Min Act: -0.1700
Data Index: 638491 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.3933. Min Act: -0.1700
Data Index: 628135 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.4558. Min Act: -0.1700
Data Index: 570829 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.4245. Min Act: -0.1700
Data Index: 79265 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.4245. Min Act: -0.1700
Data Index: 652572 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.3933. Min Act: -0.1700
Data Index: 860431 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.3307. Min Act: -0.1700
Data Index: 993246 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.3620. Min Act: -0.1700
Data Index: 1007469 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.3307. Min Act: -0.1700
Data Index: 365196 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2682. Min Act: -0.1700
Data Index: 770812 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2682. Min Act: -0.1700
Data Index: 683873 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2682. Min Act: -0.1700
Data Index: 455832 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2370. Min Act: -0.1700
Data Index: 623321 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2682. Min Act: -0.1700
Data Index: 1081267 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2370. Min Act: -0.1700
Data Index: 975706 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2995. Min Act: -0.1700
Data Index: 1163800 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2370. Min Act: -0.1700
Data Index: 1285143 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2370. Min Act: -0.1700
Data Index: 584917 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4870. Min Range: -4.4870
Max Act: 4.2370. Min Act: -0.1700
Data Index: 840392 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19