Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1065 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 3.1382. Min Range: -3.1382
Max Act: 3.1382. Min Act: -0.1700
Data Index: 124806 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.9961. Min Act: -0.1700
Data Index: 196447 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.9487. Min Act: -0.1700
Data Index: 208949 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.9645. Min Act: -0.1700
Data Index: 718167 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.9170. Min Act: -0.1700
Data Index: 284438 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8535. Min Act: -0.1700
Data Index: 968785 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8535. Min Act: -0.1700
Data Index: 884848 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8217. Min Act: -0.1700
Data Index: 449457 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8058. Min Act: -0.1700
Data Index: 709393 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8058. Min Act: -0.1700
Data Index: 329331 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8058. Min Act: -0.1700
Data Index: 69977 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7898. Min Act: -0.1700
Data Index: 1207431 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.8058. Min Act: -0.1700
Data Index: 526242 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7739. Min Act: -0.1700
Data Index: 615487 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7739. Min Act: -0.1700
Data Index: 1307995 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7739. Min Act: -0.1700
Data Index: 654597 (C4 (Web Text))
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7580. Min Act: -0.1700
Data Index: 1023230 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7739. Min Act: -0.1700
Data Index: 1332458 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7580. Min Act: -0.1700
Data Index: 890409 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1382. Min Range: -3.1382
Max Act: 2.7420. Min Act: -0.1700
Data Index: 1299374 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19