Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.8009. Min Act: -0.1700
Data Index: 1666596 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.6759. Min Act: -0.1700
Data Index: 7522863 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.6447. Min Act: -0.1700
Data Index: 470514 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.5822. Min Act: -0.1700
Data Index: 2638170 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.5822. Min Act: -0.1700
Data Index: 8115114 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.5197. Min Act: -0.1700
Data Index: 8040242 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.5197. Min Act: -0.1700
Data Index: 3834850 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4884. Min Act: -0.1700
Data Index: 8043745 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4572. Min Act: -0.1700
Data Index: 7760235 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4572. Min Act: -0.1700
Data Index: 385163 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4572. Min Act: -0.1700
Data Index: 2199287 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4259. Min Act: -0.1700
Data Index: 4326718 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4572. Min Act: -0.1700
Data Index: 2813266 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.4259. Min Act: -0.1700
Data Index: 8615650 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.3947. Min Act: -0.1700
Data Index: 4534836 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.3634. Min Act: -0.1700
Data Index: 2076175 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.3322. Min Act: -0.1700
Data Index: 8493435 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.2697. Min Act: -0.1700
Data Index: 311812 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.3009. Min Act: -0.1700
Data Index: 6562955 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8009. Min Range: -6.8009
Max Act: 6.2697. Min Act: -0.1700
Data Index: 6042051 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19