Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2020 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.1400. Min Range: -4.1400
Max Act: 4.0462. Min Act: -0.1700
Data Index: 610323 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1400. Min Range: -4.1400
Max Act: 4.1400. Min Act: -0.1700
Data Index: 798320 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9836. Min Act: -0.1700
Data Index: 683366 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1400. Min Range: -4.1400
Max Act: 4.0462. Min Act: -0.1700
Data Index: 842827 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1400. Min Range: -4.1400
Max Act: 4.0149. Min Act: -0.1700
Data Index: 498970 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 935190 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1400. Min Range: -4.1400
Max Act: 4.0149. Min Act: -0.1700
Data Index: 848281 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 413339 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 517428 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9211. Min Act: -0.1700
Data Index: 564920 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.8898. Min Act: -0.1700
Data Index: 1239395 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 186259 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9211. Min Act: -0.1700
Data Index: 444037 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9211. Min Act: -0.1700
Data Index: 553101 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9836. Min Act: -0.1700
Data Index: 675552 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9836. Min Act: -0.1700
Data Index: 700019 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 542149 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1400. Min Range: -4.1400
Max Act: 4.0149. Min Act: -0.1700
Data Index: 490862 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 829220 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1400. Min Range: -4.1400
Max Act: 3.9524. Min Act: -0.1700
Data Index: 365235 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19