Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 538 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.3677. Min Act: -0.1700
Data Index: 187652 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.3991. Min Act: -0.1700
Data Index: 653500 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2421. Min Act: -0.1700
Data Index: 1349433 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2421. Min Act: -0.1700
Data Index: 432190 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2735. Min Act: -0.1700
Data Index: 690895 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2421. Min Act: -0.1700
Data Index: 864799 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2735. Min Act: -0.1700
Data Index: 1342799 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.3049. Min Act: -0.1700
Data Index: 771389 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2421. Min Act: -0.1700
Data Index: 1187620 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2735. Min Act: -0.1700
Data Index: 438545 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2106. Min Act: -0.1700
Data Index: 720892 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2735. Min Act: -0.1700
Data Index: 609182 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2735. Min Act: -0.1700
Data Index: 745940 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.3049. Min Act: -0.1700
Data Index: 183524 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2421. Min Act: -0.1700
Data Index: 1199451 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2421. Min Act: -0.1700
Data Index: 35075 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2106. Min Act: -0.1700
Data Index: 589126 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2106. Min Act: -0.1700
Data Index: 1101511 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.1319. Min Act: -0.1700
Data Index: 35188 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3991. Min Range: -3.3991
Max Act: 3.2264. Min Act: -0.1700
Data Index: 773067 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19