Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.8858. Min Act: -0.1700
Data Index: 805072 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.7920. Min Act: -0.1700
Data Index: 4583706 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.7295. Min Act: -0.1700
Data Index: 4560167 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.6670. Min Act: -0.1700
Data Index: 4969761 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.6670. Min Act: -0.1700
Data Index: 994333 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.6670. Min Act: -0.1700
Data Index: 6784933 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.5420. Min Act: -0.1700
Data Index: 8387307 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.5420. Min Act: -0.1700
Data Index: 7220907 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.5733. Min Act: -0.1700
Data Index: 4527715 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.5420. Min Act: -0.1700
Data Index: 5627716 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4483. Min Act: -0.1700
Data Index: 7638936 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4795. Min Act: -0.1700
Data Index: 5985725 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4795. Min Act: -0.1700
Data Index: 6189001 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4483. Min Act: -0.1700
Data Index: 8567530 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4795. Min Act: -0.1700
Data Index: 3663331 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4483. Min Act: -0.1700
Data Index: 939504 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4483. Min Act: -0.1700
Data Index: 6973612 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.4170. Min Act: -0.1700
Data Index: 6026690 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.3858. Min Act: -0.1700
Data Index: 489475 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8858. Min Range: -6.8858
Max Act: 6.3858. Min Act: -0.1700
Data Index: 5390451 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19