Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1343 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.2884. Min Act: -0.1700
Data Index: 656646 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.3197. Min Act: -0.1700
Data Index: 130211 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.2572. Min Act: -0.1700
Data Index: 476415 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.2259. Min Act: -0.1700
Data Index: 27369 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.2259. Min Act: -0.1699
Data Index: 507472 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1947. Min Act: -0.1700
Data Index: 814481 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1322. Min Act: -0.1698
Data Index: 173537 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1009. Min Act: -0.1700
Data Index: 257984 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1322. Min Act: -0.1700
Data Index: 978655 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1634. Min Act: -0.1700
Data Index: 713343 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1009. Min Act: -0.1700
Data Index: 50373 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1009. Min Act: -0.1700
Data Index: 188314 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.0697. Min Act: -0.1700
Data Index: 808379 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.1009. Min Act: -0.1700
Data Index: 1066258 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.0384. Min Act: -0.1700
Data Index: 688933 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.0384. Min Act: -0.1700
Data Index: 1147544 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3197. Min Range: -6.3197
Max Act: 5.9759. Min Act: -0.1700
Data Index: 210116 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.0384. Min Act: -0.1700
Data Index: 616216 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.0072. Min Act: -0.1700
Data Index: 186367 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3197. Min Range: -6.3197
Max Act: 6.0072. Min Act: -0.1700
Data Index: 934575 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19