Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 39 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.4769. Min Act: -0.1700
Data Index: 109230 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.4456. Min Act: -0.1700
Data Index: 590192 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2886. Min Act: -0.1700
Data Index: 1065613 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2886. Min Act: -0.1700
Data Index: 357630 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2572. Min Act: -0.1700
Data Index: 349630 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2572. Min Act: -0.1700
Data Index: 52628 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2258. Min Act: -0.1700
Data Index: 106630 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2258. Min Act: -0.1700
Data Index: 997028 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2415. Min Act: -0.1700
Data Index: 417618 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2258. Min Act: -0.1700
Data Index: 299933 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2100. Min Act: -0.1700
Data Index: 121675 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2258. Min Act: -0.1700
Data Index: 975228 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2258. Min Act: -0.1700
Data Index: 582005 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.2100. Min Act: -0.1700
Data Index: 26936 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.1786. Min Act: -0.1700
Data Index: 750676 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.1943. Min Act: -0.1700
Data Index: 894995 (C4 (Web Text))
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.1943. Min Act: -0.1700
Data Index: 286181 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.1786. Min Act: -0.1700
Data Index: 356936 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.1786. Min Act: -0.1700
Data Index: 265353 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4769. Min Range: -3.4769
Max Act: 3.1628. Min Act: -0.1700
Data Index: 808787 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19