Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5022. Min Range: -8.5022
Max Act: 8.5022. Min Act: -0.1700
Data Index: 5127455 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5022. Min Range: -8.5022
Max Act: 8.4397. Min Act: -0.1700
Data Index: 7573849 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5022. Min Range: -8.5022
Max Act: 8.3772. Min Act: -0.1700
Data Index: 8312180 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5022. Min Range: -8.5022
Max Act: 8.3147. Min Act: -0.1700
Data Index: 303965 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5022. Min Range: -8.5022
Max Act: 8.1897. Min Act: -0.1700
Data Index: 6950281 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5022. Min Range: -8.5022
Max Act: 8.0647. Min Act: -0.1700
Data Index: 422087 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.9397. Min Act: -0.1700
Data Index: 6895632 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.9397. Min Act: -0.1700
Data Index: 7372064 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.9397. Min Act: -0.1700
Data Index: 2503267 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8772. Min Act: -0.1700
Data Index: 7414380 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8772. Min Act: -0.1700
Data Index: 4310437 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8772. Min Act: -0.1700
Data Index: 2607418 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8772. Min Act: -0.1700
Data Index: 6790036 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8772. Min Act: -0.1700
Data Index: 5484551 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8772. Min Act: -0.1700
Data Index: 3618237 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8147. Min Act: -0.1700
Data Index: 1759570 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8147. Min Act: -0.1700
Data Index: 1171756 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8147. Min Act: -0.1700
Data Index: 3903025 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8147. Min Act: -0.1700
Data Index: 547230 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5022. Min Range: -8.5022
Max Act: 7.8147. Min Act: -0.1700
Data Index: 2450929 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19