Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.2683. Min Act: -0.1700
Data Index: 1175430 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.2058. Min Act: -0.1700
Data Index: 4954586 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1745. Min Act: -0.1700
Data Index: 3563457 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1745. Min Act: -0.1699
Data Index: 1120542 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1433. Min Act: -0.1700
Data Index: 5882197 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1120. Min Act: -0.1700
Data Index: 1587638 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1120. Min Act: -0.1700
Data Index: 5517925 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1433. Min Act: -0.1700
Data Index: 1796989 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0808. Min Act: -0.1700
Data Index: 5876465 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0808. Min Act: -0.1700
Data Index: 946061 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0495. Min Act: -0.1700
Data Index: 7118704 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0808. Min Act: -0.1700
Data Index: 6853603 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.1120. Min Act: -0.1700
Data Index: 6267769 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0808. Min Act: -0.1700
Data Index: 6254420 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0183. Min Act: -0.1700
Data Index: 6427370 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0495. Min Act: -0.1700
Data Index: 7489884 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0495. Min Act: -0.1700
Data Index: 5188364 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8695974 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0495. Min Act: -0.1700
Data Index: 5639430 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2683. Min Range: -5.2683
Max Act: 5.0495. Min Act: -0.1700
Data Index: 1796992 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19