Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1387 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0768. Min Range: -4.0768
Max Act: 4.0768. Min Act: -0.1700
Data Index: 35316 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0768. Min Range: -4.0768
Max Act: 4.0455. Min Act: -0.1700
Data Index: 546448 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0768. Min Range: -4.0768
Max Act: 4.0455. Min Act: -0.1700
Data Index: 563837 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.9517. Min Act: -0.1700
Data Index: 209229 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.9517. Min Act: -0.1700
Data Index: 1266729 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.9204. Min Act: -0.1700
Data Index: 145674 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.8892. Min Act: -0.1700
Data Index: 614373 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.9204. Min Act: -0.1700
Data Index: 532882 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.9204. Min Act: -0.1700
Data Index: 74711 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.8579. Min Act: -0.1700
Data Index: 698550 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.8892. Min Act: -0.1700
Data Index: 1256366 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.8266. Min Act: -0.1700
Data Index: 1238938 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.8579. Min Act: -0.1700
Data Index: 575075 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7953. Min Act: -0.1700
Data Index: 196537 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7953. Min Act: -0.1700
Data Index: 820447 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7640. Min Act: -0.1700
Data Index: 1116483 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7640. Min Act: -0.1700
Data Index: 159135 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7640. Min Act: -0.1700
Data Index: 720078 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7015. Min Act: -0.1700
Data Index: 451351 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0768. Min Range: -4.0768
Max Act: 3.7015. Min Act: -0.1700
Data Index: 1232364 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19