Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 905 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.9386. Min Act: -0.1700
Data Index: 247072 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.9228. Min Act: -0.1700
Data Index: 1593221 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8593. Min Act: -0.1700
Data Index: 1181258 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8752. Min Act: -0.1700
Data Index: 1555694 (Python Code)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8752. Min Act: -0.1700
Data Index: 1634460 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8752. Min Act: -0.1700
Data Index: 1508072 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8911. Min Act: -0.1700
Data Index: 461302 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8911. Min Act: -0.1700
Data Index: 955533 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8752. Min Act: -0.1700
Data Index: 1463220 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8911. Min Act: -0.1700
Data Index: 79183 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8752. Min Act: -0.1700
Data Index: 243438 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8752. Min Act: -0.1700
Data Index: 524845 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8275. Min Act: -0.1700
Data Index: 850669 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8434. Min Act: -0.1700
Data Index: 138987 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8434. Min Act: -0.1700
Data Index: 244939 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8275. Min Act: -0.1700
Data Index: 1446859 (Python Code)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8275. Min Act: -0.1700
Data Index: 1639996 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8275. Min Act: -0.1700
Data Index: 389934 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8275. Min Act: -0.1700
Data Index: 137472 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9386. Min Range: -2.9386
Max Act: 2.8275. Min Act: -0.1700
Data Index: 1524135 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19