Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 743 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.9203. Min Act: -0.1700
Data Index: 1172632 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.8890. Min Act: -0.1700
Data Index: 416448 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.8265. Min Act: -0.1700
Data Index: 65913 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7796. Min Act: -0.1700
Data Index: 124254 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7796. Min Act: -0.1700
Data Index: 18733 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.8265. Min Act: -0.1700
Data Index: 1042320 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7952. Min Act: -0.1700
Data Index: 367977 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7952. Min Act: -0.1700
Data Index: 1295428 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7952. Min Act: -0.1700
Data Index: 1347030 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7639. Min Act: -0.1700
Data Index: 640073 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7639. Min Act: -0.1700
Data Index: 775006 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7952. Min Act: -0.1700
Data Index: 787473 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7796. Min Act: -0.1700
Data Index: 457883 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7639. Min Act: -0.1700
Data Index: 750380 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7796. Min Act: -0.1700
Data Index: 519132 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7639. Min Act: -0.1700
Data Index: 1182305 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7483. Min Act: -0.1700
Data Index: 118886 (C4 (Web Text))
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7639. Min Act: -0.1700
Data Index: 490577 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7796. Min Act: -0.1700
Data Index: 1161542 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9203. Min Range: -3.9203
Max Act: 3.7326. Min Act: -0.1700
Data Index: 231948 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19