Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 170 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.4371. Min Act: -0.1700
Data Index: 83990 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.4208. Min Act: -0.1700
Data Index: 1556692 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.4208. Min Act: -0.1700
Data Index: 403374 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3882. Min Act: -0.1700
Data Index: 1195375 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3882. Min Act: -0.1700
Data Index: 390549 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3718. Min Act: -0.1700
Data Index: 1554517 (Python Code)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3882. Min Act: -0.1698
Data Index: 80535 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3718. Min Act: -0.1700
Data Index: 872015 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3718. Min Act: -0.1700
Data Index: 146853 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3718. Min Act: -0.1700
Data Index: 2138 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3391. Min Act: -0.1698
Data Index: 1157840 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3391. Min Act: -0.1698
Data Index: 206624 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3555. Min Act: -0.1700
Data Index: 575038 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3227. Min Act: -0.1700
Data Index: 341362 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3227. Min Act: -0.1700
Data Index: 447394 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3227. Min Act: -0.1689
Data Index: 1183174 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3227. Min Act: -0.1700
Data Index: 1041001 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3227. Min Act: -0.1699
Data Index: 1566434 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3063. Min Act: -0.1699
Data Index: 783332 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4371. Min Range: -2.4371
Max Act: 2.3063. Min Act: -0.1675
Data Index: 547884 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19