Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 480 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.5595. Min Act: -0.1700
Data Index: 1152027 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.5111. Min Act: -0.1700
Data Index: 20581 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.5272. Min Act: -0.1700
Data Index: 78479 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4462. Min Act: -0.1700
Data Index: 707117 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4299. Min Act: -0.1700
Data Index: 973163 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4299. Min Act: -0.1700
Data Index: 254310 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4299. Min Act: -0.1700
Data Index: 1234677 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4136. Min Act: -0.1700
Data Index: 491182 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4136. Min Act: -0.1700
Data Index: 818842 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.4136. Min Act: -0.1700
Data Index: 329718 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3973. Min Act: -0.1700
Data Index: 1098893 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3973. Min Act: -0.1700
Data Index: 71283 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3973. Min Act: -0.1700
Data Index: 111015 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 589876 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 346233 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 838764 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 1120389 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 214848 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 16156 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5595. Min Range: -2.5595
Max Act: 2.3810. Min Act: -0.1700
Data Index: 1152527 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19