Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1641 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.6706. Min Act: -0.1700
Data Index: 255979 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.5456. Min Act: -0.1700
Data Index: 333942 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.4831. Min Act: -0.1700
Data Index: 4616 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.4362. Min Act: -0.1700
Data Index: 849870 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.3737. Min Act: -0.1700
Data Index: 393157 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.3737. Min Act: -0.1700
Data Index: 1175529 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.3893. Min Act: -0.1700
Data Index: 348240 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2956. Min Act: -0.1700
Data Index: 1064521 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.3737. Min Act: -0.1700
Data Index: 1302449 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.3737. Min Act: -0.1700
Data Index: 492600 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2956. Min Act: -0.1700
Data Index: 916162 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2956. Min Act: -0.1700
Data Index: 389342 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2331. Min Act: -0.1700
Data Index: 1033579 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.1862. Min Act: -0.1700
Data Index: 352403 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2643. Min Act: -0.1700
Data Index: 303676 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2799. Min Act: -0.1700
Data Index: 1153120 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2487. Min Act: -0.1700
Data Index: 464135 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2487. Min Act: -0.1700
Data Index: 282755 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2487. Min Act: -0.1700
Data Index: 1025619 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6706. Min Range: -4.6706
Max Act: 4.2487. Min Act: -0.1700
Data Index: 283261 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19