Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 99 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 5.0983. Min Range: -5.0983
Max Act: 5.0983. Min Act: -0.1700
Data Index: 1431824 (Python Code)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9733. Min Act: -0.1700
Data Index: 1625638 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9108. Min Act: -0.1700
Data Index: 1558576 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9421. Min Act: -0.1700
Data Index: 1523190 (Python Code)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9421. Min Act: -0.1700
Data Index: 1529333 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9108. Min Act: -0.1700
Data Index: 784242 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1455212 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1644455 (Python Code)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9108. Min Act: -0.1700
Data Index: 1493118 (Python Code)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1439241 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8483. Min Act: -0.1700
Data Index: 1398108 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8171. Min Act: -0.1700
Data Index: 1376954 (Python Code)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.9108. Min Act: -0.1700
Data Index: 1534975 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8483. Min Act: -0.1700
Data Index: 1468716 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8171. Min Act: -0.1700
Data Index: 1439445 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1486089 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8483. Min Act: -0.1700
Data Index: 1391456 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8796. Min Act: -0.1700
Data Index: 1460505 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8171. Min Act: -0.1700
Data Index: 1554501 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0983. Min Range: -5.0983
Max Act: 4.8171. Min Act: -0.1700
Data Index: 1451138 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19