Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2549 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2794. Min Range: -9.2794
Max Act: 9.2794. Min Act: -0.1700
Data Index: 8413658 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2794. Min Range: -9.2794
Max Act: 9.1544. Min Act: -0.1700
Data Index: 150868 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2794. Min Range: -9.2794
Max Act: 9.0919. Min Act: -0.1700
Data Index: 4593646 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.9669. Min Act: -0.1700
Data Index: 7596227 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.9669. Min Act: -0.1700
Data Index: 7988319 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.9044. Min Act: -0.1700
Data Index: 654075 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.9044. Min Act: -0.1700
Data Index: 4574870 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.9669. Min Act: -0.1700
Data Index: 3210719 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.8419. Min Act: -0.1700
Data Index: 5627947 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7169. Min Act: -0.1700
Data Index: 3484823 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7794. Min Act: -0.1700
Data Index: 8639797 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7794. Min Act: -0.1700
Data Index: 331761 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7794. Min Act: -0.1700
Data Index: 7413998 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7169. Min Act: -0.1700
Data Index: 5753171 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7169. Min Act: -0.1700
Data Index: 6983758 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7169. Min Act: -0.1700
Data Index: 4376001 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.7169. Min Act: -0.1700
Data Index: 1656569 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.5919. Min Act: -0.1700
Data Index: 2741822 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.6544. Min Act: -0.1700
Data Index: 5444823 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2794. Min Range: -9.2794
Max Act: 8.6544. Min Act: -0.1700
Data Index: 2238322 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19