Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 442 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.5520. Min Act: -0.1700
Data Index: 1201344 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4711. Min Act: -0.1700
Data Index: 498249 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4873. Min Act: -0.1700
Data Index: 314747 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4548. Min Act: -0.1700
Data Index: 580064 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4386. Min Act: -0.1700
Data Index: 1254141 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4386. Min Act: -0.1700
Data Index: 988270 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4711. Min Act: -0.1700
Data Index: 687489 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4386. Min Act: -0.1700
Data Index: 1413112 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4386. Min Act: -0.1700
Data Index: 156868 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4223. Min Act: -0.1700
Data Index: 156770 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4223. Min Act: -0.1700
Data Index: 276181 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4060. Min Act: -0.1700
Data Index: 67367 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4386. Min Act: -0.1700
Data Index: 123420 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4223. Min Act: -0.1700
Data Index: 1419896 (Python Code)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4223. Min Act: -0.1700
Data Index: 1509961 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4060. Min Act: -0.1700
Data Index: 1421348 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.3897. Min Act: -0.1700
Data Index: 1543506 (Python Code)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.3897. Min Act: -0.1700
Data Index: 1316350 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4060. Min Act: -0.1700
Data Index: 282786 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5520. Min Range: -2.5520
Max Act: 2.4223. Min Act: -0.1700
Data Index: 223377 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19