Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1927 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.7458. Min Act: -0.1700
Data Index: 751088 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.7458. Min Act: -0.1700
Data Index: 86504 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.7458. Min Act: -0.1700
Data Index: 100405 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.7298. Min Act: -0.1700
Data Index: 267399 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.7298. Min Act: -0.1700
Data Index: 348223 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6818. Min Act: -0.1700
Data Index: 1456155 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6658. Min Act: -0.1700
Data Index: 1488533 (Python Code)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6658. Min Act: -0.1700
Data Index: 1220551 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6658. Min Act: -0.1700
Data Index: 89608 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6658. Min Act: -0.1700
Data Index: 988640 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6658. Min Act: -0.1700
Data Index: 148309 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6497. Min Act: -0.1700
Data Index: 61505 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6337. Min Act: -0.1700
Data Index: 311414 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6337. Min Act: -0.1700
Data Index: 423474 (C4 (Web Text))
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6176. Min Act: -0.1700
Data Index: 570596 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6176. Min Act: -0.1700
Data Index: 219049 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6176. Min Act: -0.1700
Data Index: 1297457 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6176. Min Act: -0.1700
Data Index: 470684 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6176. Min Act: -0.1700
Data Index: 957799 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7458. Min Range: -2.7458
Max Act: 2.6176. Min Act: -0.1700
Data Index: 1079290 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19