Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 209 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.8055. Min Act: -0.1700
Data Index: 443108 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.7417. Min Act: -0.1700
Data Index: 1127100 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.7577. Min Act: -0.1700
Data Index: 1315395 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.7417. Min Act: -0.1700
Data Index: 501082 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.7258. Min Act: -0.1700
Data Index: 854157 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.7098. Min Act: -0.1700
Data Index: 1106731 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6778. Min Act: -0.1700
Data Index: 914096 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6938. Min Act: -0.1700
Data Index: 793132 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6617. Min Act: -0.1700
Data Index: 1055336 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6617. Min Act: -0.1700
Data Index: 869495 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6617. Min Act: -0.1700
Data Index: 924163 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6778. Min Act: -0.1700
Data Index: 649067 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6617. Min Act: -0.1700
Data Index: 1296830 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6778. Min Act: -0.1700
Data Index: 701184 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6778. Min Act: -0.1700
Data Index: 244470 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6457. Min Act: -0.1700
Data Index: 343332 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6296. Min Act: -0.1700
Data Index: 27089 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6296. Min Act: -0.1700
Data Index: 1163449 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6296. Min Act: -0.1700
Data Index: 72317 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8055. Min Range: -2.8055
Max Act: 2.6778. Min Act: -0.1700
Data Index: 238004 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19