Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 301 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.6552. Min Act: -0.1700
Data Index: 955405 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.6552. Min Act: -0.1700
Data Index: 1270420 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.6231. Min Act: -0.1700
Data Index: 79291 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.6231. Min Act: -0.1700
Data Index: 149160 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.6071. Min Act: -0.1700
Data Index: 220280 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5748. Min Act: -0.1700
Data Index: 196112 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5748. Min Act: -0.1700
Data Index: 419152 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5748. Min Act: -0.1700
Data Index: 444654 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5587. Min Act: -0.1700
Data Index: 965546 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5426. Min Act: -0.1700
Data Index: 435459 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5587. Min Act: -0.1700
Data Index: 13021 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5426. Min Act: -0.1700
Data Index: 70105 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5264. Min Act: -0.1700
Data Index: 397101 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5102. Min Act: -0.1700
Data Index: 837208 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5102. Min Act: -0.1700
Data Index: 1283084 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.4941. Min Act: -0.1700
Data Index: 913411 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.4778. Min Act: -0.1700
Data Index: 223603 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.5264. Min Act: -0.1700
Data Index: 1209313 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.4778. Min Act: -0.1700
Data Index: 805159 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6552. Min Range: -2.6552
Max Act: 2.4778. Min Act: -0.1700
Data Index: 1074245 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19