Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1976 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.5252. Min Act: -0.1700
Data Index: 842835 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.5091. Min Act: -0.1700
Data Index: 1191003 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4929. Min Act: -0.1700
Data Index: 863884 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4929. Min Act: -0.1700
Data Index: 596720 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4604. Min Act: -0.1700
Data Index: 244507 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4604. Min Act: -0.1700
Data Index: 1270058 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4279. Min Act: -0.1700
Data Index: 637562 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4604. Min Act: -0.1700
Data Index: 1310674 (C4 (Web Text))
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4279. Min Act: -0.1700
Data Index: 862085 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4279. Min Act: -0.1700
Data Index: 722747 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4442. Min Act: -0.1700
Data Index: 1352813 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4116. Min Act: -0.1700
Data Index: 1075967 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4116. Min Act: -0.1700
Data Index: 784836 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4279. Min Act: -0.1700
Data Index: 1323215 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4279. Min Act: -0.1700
Data Index: 544200 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.3953. Min Act: -0.1700
Data Index: 1303119 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4116. Min Act: -0.1700
Data Index: 94257 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4116. Min Act: -0.1700
Data Index: 872318 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4116. Min Act: -0.1700
Data Index: 917214 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5252. Min Range: -2.5252
Max Act: 2.4116. Min Act: -0.1700
Data Index: 244448 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19