Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1835 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.8883. Min Act: -0.1700
Data Index: 403297 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.8565. Min Act: -0.1700
Data Index: 185035 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7769. Min Act: -0.1700
Data Index: 321882 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7610. Min Act: -0.1700
Data Index: 971372 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7450. Min Act: -0.1700
Data Index: 675487 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7450. Min Act: -0.1700
Data Index: 1288276 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7131. Min Act: -0.1700
Data Index: 757480 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7291. Min Act: -0.1700
Data Index: 735667 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.7131. Min Act: -0.1700
Data Index: 87288 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6971. Min Act: -0.1700
Data Index: 105705 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6971. Min Act: -0.1700
Data Index: 1326147 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6650. Min Act: -0.1700
Data Index: 816359 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6811. Min Act: -0.1700
Data Index: 950777 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6650. Min Act: -0.1700
Data Index: 638238 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6811. Min Act: -0.1700
Data Index: 1100197 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6650. Min Act: -0.1700
Data Index: 979731 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6650. Min Act: -0.1700
Data Index: 531061 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6490. Min Act: -0.1700
Data Index: 372931 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6490. Min Act: -0.1700
Data Index: 733680 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8883. Min Range: -2.8883
Max Act: 2.6490. Min Act: -0.1700
Data Index: 493836 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19