Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1967 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.8118. Min Act: -0.1700
Data Index: 63001 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7959. Min Act: -0.1700
Data Index: 319016 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7640. Min Act: -0.1700
Data Index: 649641 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7640. Min Act: -0.1700
Data Index: 124287 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7640. Min Act: -0.1700
Data Index: 1320478 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7481. Min Act: -0.1700
Data Index: 596939 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 606240 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7481. Min Act: -0.1700
Data Index: 395128 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7481. Min Act: -0.1700
Data Index: 966122 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7481. Min Act: -0.1700
Data Index: 414545 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7161. Min Act: -0.1700
Data Index: 680551 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 1107275 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 1237450 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7161. Min Act: -0.1700
Data Index: 385750 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 942341 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 191215 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7161. Min Act: -0.1700
Data Index: 980580 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 1000800 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7161. Min Act: -0.1700
Data Index: 1050441 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8118. Min Range: -2.8118
Max Act: 2.7321. Min Act: -0.1700
Data Index: 670963 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19