Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2047 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.3671. Min Act: -0.1700
Data Index: 807873 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.3671. Min Act: -0.1700
Data Index: 546191 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.3045. Min Act: -0.1700
Data Index: 1121590 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1313324 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 1311435 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 190036 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 916643 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2420. Min Act: -0.1700
Data Index: 861803 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 744874 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2733. Min Act: -0.1700
Data Index: 617354 (C4 (Web Text))
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 895653 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2420. Min Act: -0.1700
Data Index: 459979 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2420. Min Act: -0.1700
Data Index: 689353 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 817792 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.1795. Min Act: -0.1700
Data Index: 301863 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.2108. Min Act: -0.1700
Data Index: 287735 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.1483. Min Act: -0.1700
Data Index: 543221 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.1483. Min Act: -0.1700
Data Index: 46758 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.1483. Min Act: -0.1700
Data Index: 40880 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3671. Min Range: -4.3671
Max Act: 4.1483. Min Act: -0.1700
Data Index: 213112 (C4 (Web Text))
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19