Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 735 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.9626. Min Act: -0.1700
Data Index: 890891 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.6601. Min Act: -0.1700
Data Index: 528673 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.6441. Min Act: -0.1700
Data Index: 339106 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.6441. Min Act: -0.1700
Data Index: 358783 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5797. Min Act: -0.1700
Data Index: 532026 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5958. Min Act: -0.1700
Data Index: 516479 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.6280. Min Act: -0.1700
Data Index: 756462 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5797. Min Act: -0.1700
Data Index: 648966 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5797. Min Act: -0.1700
Data Index: 841722 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5958. Min Act: -0.1700
Data Index: 1317186 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5797. Min Act: -0.1700
Data Index: 324365 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5636. Min Act: -0.1700
Data Index: 160758 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.4990. Min Act: -0.1700
Data Index: 15748 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5475. Min Act: -0.1700
Data Index: 296392 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5313. Min Act: -0.1700
Data Index: 880611 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.5313. Min Act: -0.1700
Data Index: 591163 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.4990. Min Act: -0.1700
Data Index: 951067 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.4990. Min Act: -0.1700
Data Index: 1130659 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.4990. Min Act: -0.1700
Data Index: 842997 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9626. Min Range: -2.9626
Max Act: 2.4990. Min Act: -0.1700
Data Index: 1316272 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19