Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1703 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.0282. Min Range: -4.0282
Max Act: 4.0282. Min Act: -0.1700
Data Index: 1474561 (Python Code)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0282. Min Range: -4.0282
Max Act: 4.0282. Min Act: -0.1700
Data Index: 1409952 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0282. Min Range: -4.0282
Max Act: 4.0282. Min Act: -0.1700
Data Index: 1586697 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1530449 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1604368 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1601586 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1371604 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9969. Min Act: -0.1700
Data Index: 1494365 (Python Code)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1642872 (Python Code)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1577264 (Python Code)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1583485 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1583245 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1442416 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1567975 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1558179 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1551419 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1427925 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1419323 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9657. Min Act: -0.1700
Data Index: 1377230 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0282. Min Range: -4.0282
Max Act: 3.9031. Min Act: -0.1700
Data Index: 1490345 (Python Code)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19