Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.3100. Min Act: -0.1700
Data Index: 312693 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.2475. Min Act: -0.1700
Data Index: 1040122 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.2475. Min Act: -0.1700
Data Index: 492677 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.2475. Min Act: -0.1700
Data Index: 650755 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.2162. Min Act: -0.1700
Data Index: 412602 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.1849. Min Act: -0.1700
Data Index: 955928 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.1537. Min Act: -0.1700
Data Index: 248217 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.1537. Min Act: -0.1700
Data Index: 1283735 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.1224. Min Act: -0.1700
Data Index: 1178886 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0912. Min Act: -0.1700
Data Index: 1312550 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.1224. Min Act: -0.1700
Data Index: 789131 (C4 (Web Text))
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0599. Min Act: -0.1700
Data Index: 483151 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0912. Min Act: -0.1700
Data Index: 849944 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0599. Min Act: -0.1700
Data Index: 915283 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0912. Min Act: -0.1699
Data Index: 768670 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0912. Min Act: -0.1700
Data Index: 334116 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0599. Min Act: -0.1700
Data Index: 571378 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0912. Min Act: -0.1700
Data Index: 680901 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0599. Min Act: -0.1700
Data Index: 466005 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3100. Min Range: -4.3100
Max Act: 4.0599. Min Act: -0.1699
Data Index: 1328673 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19