Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.7050. Min Act: -0.1700
Data Index: 4502335 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.6737. Min Act: -0.1700
Data Index: 5386793 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.6737. Min Act: -0.1700
Data Index: 7965152 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.6112. Min Act: -0.1700
Data Index: 2092149 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.5487. Min Act: -0.1700
Data Index: 4022201 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.5175. Min Act: -0.1700
Data Index: 1303000 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.5175. Min Act: -0.1700
Data Index: 2435892 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.5175. Min Act: -0.1700
Data Index: 7508918 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.5175. Min Act: -0.1700
Data Index: 148937 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.5175. Min Act: -0.1700
Data Index: 6949093 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4862. Min Act: -0.1700
Data Index: 6211326 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4862. Min Act: -0.1700
Data Index: 6495878 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4862. Min Act: -0.1700
Data Index: 401263 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4237. Min Act: -0.1700
Data Index: 2657682 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4550. Min Act: -0.1700
Data Index: 3182997 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4550. Min Act: -0.1700
Data Index: 2838571 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4237. Min Act: -0.1700
Data Index: 533945 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4237. Min Act: -0.1700
Data Index: 6011018 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.3925. Min Act: -0.1700
Data Index: 2545857 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7050. Min Range: -5.7050
Max Act: 5.4237. Min Act: -0.1700
Data Index: 4292282 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19