Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.3173. Min Act: -0.1700
Data Index: 6936896 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.1922. Min Act: -0.1700
Data Index: 6437417 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.1922. Min Act: -0.1700
Data Index: 6460369 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.1297. Min Act: -0.1700
Data Index: 4832132 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.1297. Min Act: -0.1700
Data Index: 2339492 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0985. Min Act: -0.1700
Data Index: 4832148 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0985. Min Act: -0.1700
Data Index: 6936881 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0985. Min Act: -0.1700
Data Index: 3227834 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0672. Min Act: -0.1700
Data Index: 7588437 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0047. Min Act: -0.1700
Data Index: 1477693 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0360. Min Act: -0.1700
Data Index: 190433 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0360. Min Act: -0.1700
Data Index: 190424 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0360. Min Act: -0.1700
Data Index: 5028843 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3173. Min Range: -4.3173
Max Act: 4.0047. Min Act: -0.1700
Data Index: 4362039 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3173. Min Range: -4.3173
Max Act: 3.9734. Min Act: -0.1700
Data Index: 7218566 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3173. Min Range: -4.3173
Max Act: 3.9734. Min Act: -0.1700
Data Index: 7068417 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3173. Min Range: -4.3173
Max Act: 3.9734. Min Act: -0.1700
Data Index: 7732293 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3173. Min Range: -4.3173
Max Act: 3.9422. Min Act: -0.1700
Data Index: 6094496 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3173. Min Range: -4.3173
Max Act: 3.9422. Min Act: -0.1700
Data Index: 6777598 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3173. Min Range: -4.3173
Max Act: 3.9422. Min Act: -0.1700
Data Index: 2910264 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19