Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 466 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.4822. Min Act: -0.1700
Data Index: 292273 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.4497. Min Act: -0.1700
Data Index: 798720 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.4497. Min Act: -0.1700
Data Index: 437223 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.4172. Min Act: -0.1700
Data Index: 1140061 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.4172. Min Act: -0.1700
Data Index: 1182653 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3845. Min Act: -0.1700
Data Index: 151952 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3682. Min Act: -0.1700
Data Index: 542217 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3682. Min Act: -0.1700
Data Index: 719302 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3518. Min Act: -0.1700
Data Index: 1096738 (C4 (Web Text))
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 192095 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3518. Min Act: -0.1700
Data Index: 475706 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3682. Min Act: -0.1700
Data Index: 86199 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 770115 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 464727 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3518. Min Act: -0.1700
Data Index: 320077 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 1186966 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 1174259 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 909009 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3190. Min Act: -0.1700
Data Index: 505160 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4822. Min Range: -2.4822
Max Act: 2.3354. Min Act: -0.1700
Data Index: 746667 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19