Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1044 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.9542. Min Act: -0.1700
Data Index: 123087 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.8908. Min Act: -0.1700
Data Index: 1292802 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.8273. Min Act: -0.1700
Data Index: 719654 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.8273. Min Act: -0.1700
Data Index: 330544 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.8114. Min Act: -0.1700
Data Index: 440757 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.7476. Min Act: -0.1700
Data Index: 861193 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.7476. Min Act: -0.1700
Data Index: 1293904 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.7316. Min Act: -0.1700
Data Index: 1025897 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.7157. Min Act: -0.1700
Data Index: 422495 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6997. Min Act: -0.1700
Data Index: 252023 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.7157. Min Act: -0.1700
Data Index: 527776 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6997. Min Act: -0.1700
Data Index: 1289651 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6997. Min Act: -0.1700
Data Index: 143709 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6837. Min Act: -0.1700
Data Index: 432892 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6997. Min Act: -0.1700
Data Index: 235465 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6837. Min Act: -0.1700
Data Index: 935464 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6837. Min Act: -0.1700
Data Index: 6073 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6837. Min Act: -0.1700
Data Index: 561523 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6837. Min Act: -0.1700
Data Index: 251440 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9542. Min Range: -2.9542
Max Act: 2.6676. Min Act: -0.1700
Data Index: 512571 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19