Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 867 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 367900 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 212391 (C4 (Web Text))
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 449811 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2673. Min Act: -0.1700
Data Index: 639672 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1736. Min Act: -0.1700
Data Index: 265505 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2048. Min Act: -0.1700
Data Index: 264166 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2361. Min Act: -0.1700
Data Index: 568124 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1110. Min Act: -0.1700
Data Index: 225348 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1423. Min Act: -0.1700
Data Index: 1018259 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1110. Min Act: -0.1700
Data Index: 629102 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2048. Min Act: -0.1700
Data Index: 684616 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1110. Min Act: -0.1700
Data Index: 181451 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1736. Min Act: -0.1700
Data Index: 624671 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1736. Min Act: -0.1700
Data Index: 329379 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1110. Min Act: -0.1700
Data Index: 107416 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1423. Min Act: -0.1700
Data Index: 925822 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.2048. Min Act: -0.1700
Data Index: 1095442 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1736. Min Act: -0.1700
Data Index: 1138185 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1736. Min Act: -0.1700
Data Index: 102712 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2673. Min Range: -4.2673
Max Act: 4.1736. Min Act: -0.1700
Data Index: 422897 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19