Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 205 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0149. Min Range: -4.0149
Max Act: 4.0149. Min Act: -0.1700
Data Index: 1183583 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8586. Min Act: -0.1700
Data Index: 384511 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8586. Min Act: -0.1700
Data Index: 637793 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8899. Min Act: -0.1700
Data Index: 628570 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8586. Min Act: -0.1700
Data Index: 1183719 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8586. Min Act: -0.1700
Data Index: 1257377 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8273. Min Act: -0.1700
Data Index: 737477 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8273. Min Act: -0.1700
Data Index: 791071 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.8273. Min Act: -0.1700
Data Index: 593601 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7960. Min Act: -0.1700
Data Index: 736389 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7960. Min Act: -0.1700
Data Index: 638192 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7647. Min Act: -0.1700
Data Index: 103883 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7647. Min Act: -0.1700
Data Index: 911395 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7647. Min Act: -0.1700
Data Index: 919527 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7022. Min Act: -0.1700
Data Index: 1084935 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7647. Min Act: -0.1700
Data Index: 333495 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7022. Min Act: -0.1700
Data Index: 476288 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7335. Min Act: -0.1700
Data Index: 300321 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7022. Min Act: -0.1700
Data Index: 907553 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0149. Min Range: -4.0149
Max Act: 3.7022. Min Act: -0.1700
Data Index: 386190 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19