Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 41 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3818. Min Act: -0.1700
Data Index: 391252 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3818. Min Act: -0.1700
Data Index: 1022681 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3505. Min Act: -0.1700
Data Index: 819846 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3193. Min Act: -0.1700
Data Index: 449191 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3193. Min Act: -0.1700
Data Index: 325514 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3505. Min Act: -0.1700
Data Index: 871719 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3193. Min Act: -0.1700
Data Index: 687217 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3193. Min Act: -0.1700
Data Index: 181674 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 1293240 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.3193. Min Act: -0.1700
Data Index: 984382 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 557251 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 1161369 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 820959 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2880. Min Act: -0.1700
Data Index: 415309 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2568. Min Act: -0.1700
Data Index: 865449 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2568. Min Act: -0.1700
Data Index: 1308297 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2568. Min Act: -0.1700
Data Index: 1217451 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2568. Min Act: -0.1700
Data Index: 268307 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2568. Min Act: -0.1700
Data Index: 2753 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3818. Min Range: -4.3818
Max Act: 4.2568. Min Act: -0.1700
Data Index: 410491 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19