Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0989. Min Range: -6.0989
Max Act: 6.0989. Min Act: -0.1700
Data Index: 2339026 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.7864. Min Act: -0.1700
Data Index: 4892675 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.7864. Min Act: -0.1700
Data Index: 8206061 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.6927. Min Act: -0.1700
Data Index: 4909961 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.7239. Min Act: -0.1700
Data Index: 6254274 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.6927. Min Act: -0.1700
Data Index: 238291 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.5989. Min Act: -0.1700
Data Index: 7790398 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.5364. Min Act: -0.1700
Data Index: 219410 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.5364. Min Act: -0.1700
Data Index: 6113309 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.5052. Min Act: -0.1700
Data Index: 2646663 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.5052. Min Act: -0.1700
Data Index: 7621788 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4739. Min Act: -0.1700
Data Index: 8638676 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4739. Min Act: -0.1700
Data Index: 6879585 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4739. Min Act: -0.1700
Data Index: 5340592 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4739. Min Act: -0.1700
Data Index: 7833527 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4427. Min Act: -0.1700
Data Index: 5228433 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4427. Min Act: -0.1700
Data Index: 723676 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4427. Min Act: -0.1700
Data Index: 932336 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4114. Min Act: -0.1700
Data Index: 6956825 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0989. Min Range: -6.0989
Max Act: 5.4114. Min Act: -0.1700
Data Index: 1316613 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19