Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1105 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.4264. Min Act: -0.1700
Data Index: 176350 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0982. Min Act: -0.1700
Data Index: 1089023 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0826. Min Act: -0.1700
Data Index: 63262 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0826. Min Act: -0.1700
Data Index: 269126 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0201. Min Act: -0.1700
Data Index: 1087232 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0357. Min Act: -0.1700
Data Index: 528507 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0513. Min Act: -0.1700
Data Index: 1278316 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0357. Min Act: -0.1700
Data Index: 490270 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0201. Min Act: -0.1700
Data Index: 599095 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0044. Min Act: -0.1700
Data Index: 15062 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4264. Min Range: -4.4264
Max Act: 4.0044. Min Act: -0.1700
Data Index: 1084165 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9888. Min Act: -0.1700
Data Index: 206682 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9575. Min Act: -0.1700
Data Index: 745116 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9575. Min Act: -0.1700
Data Index: 568472 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9419. Min Act: -0.1700
Data Index: 598326 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9263. Min Act: -0.1700
Data Index: 44965 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9106. Min Act: -0.1700
Data Index: 792589 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9263. Min Act: -0.1700
Data Index: 314814 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9263. Min Act: -0.1700
Data Index: 278949 (C4 (Web Text))
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4264. Min Range: -4.4264
Max Act: 3.9106. Min Act: -0.1700
Data Index: 360833 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19