Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1990 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.8312. Min Act: -0.1700
Data Index: 599393 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7835. Min Act: -0.1700
Data Index: 466574 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7675. Min Act: -0.1700
Data Index: 495559 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7516. Min Act: -0.1700
Data Index: 1185193 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7356. Min Act: -0.1700
Data Index: 834060 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7196. Min Act: -0.1700
Data Index: 106661 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7196. Min Act: -0.1700
Data Index: 972031 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7036. Min Act: -0.1700
Data Index: 383930 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7036. Min Act: -0.1700
Data Index: 391964 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7036. Min Act: -0.1700
Data Index: 550940 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 917050 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 33225 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7196. Min Act: -0.1700
Data Index: 147532 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.7036. Min Act: -0.1700
Data Index: 579248 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6716. Min Act: -0.1700
Data Index: 511805 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 32266 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 620196 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 374281 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 1136301 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8312. Min Range: -2.8312
Max Act: 2.6876. Min Act: -0.1700
Data Index: 682393 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19