Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2008 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.7232. Min Act: -0.1700
Data Index: 906566 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.6295. Min Act: -0.1700
Data Index: 255696 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5670. Min Act: -0.1700
Data Index: 765391 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5982. Min Act: -0.1700
Data Index: 844348 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5982. Min Act: -0.1699
Data Index: 1030454 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5044. Min Act: -0.1700
Data Index: 224851 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5357. Min Act: -0.1700
Data Index: 1132529 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5044. Min Act: -0.1700
Data Index: 1341144 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5044. Min Act: -0.1700
Data Index: 705246 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5357. Min Act: -0.1700
Data Index: 1344930 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5357. Min Act: -0.1700
Data Index: 1145772 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5044. Min Act: -0.1700
Data Index: 87259 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5044. Min Act: -0.1700
Data Index: 152241 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5670. Min Act: -0.1700
Data Index: 1096109 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5357. Min Act: -0.1700
Data Index: 1127454 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.4732. Min Act: -0.1700
Data Index: 281301 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5044. Min Act: -0.1700
Data Index: 588597 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.4419. Min Act: -0.1700
Data Index: 339608 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.4419. Min Act: -0.1700
Data Index: 1345437 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7232. Min Range: -4.7232
Max Act: 4.5357. Min Act: -0.1700
Data Index: 70126 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19