Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 280 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.3025. Min Act: -0.1700
Data Index: 566670 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.5525. Min Act: -0.1700
Data Index: 80294 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.1463. Min Act: -0.1700
Data Index: 1088778 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.3650. Min Act: -0.1700
Data Index: 820183 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.3650. Min Act: -0.1700
Data Index: 210894 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.2713. Min Act: -0.1700
Data Index: 989347 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.1463. Min Act: -0.1700
Data Index: 361884 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.1775. Min Act: -0.1700
Data Index: 90036 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.0838. Min Act: -0.1700
Data Index: 408362 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.9900. Min Act: -0.1700
Data Index: 160897 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5525. Min Range: -6.5525
Max Act: 6.0525. Min Act: -0.1699
Data Index: 786486 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.9900. Min Act: -0.1699
Data Index: 1340019 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.8963. Min Act: -0.1700
Data Index: 579052 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.9275. Min Act: -0.1700
Data Index: 307981 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.6463. Min Act: -0.1700
Data Index: 68567 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.8025. Min Act: -0.1700
Data Index: 650602 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.9275. Min Act: -0.1700
Data Index: 772700 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.9900. Min Act: -0.1700
Data Index: 699458 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.9275. Min Act: -0.1700
Data Index: 642199 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5525. Min Range: -6.5525
Max Act: 5.8025. Min Act: -0.1700
Data Index: 166714 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19