Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3807 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5662. Min Act: -0.1700
Data Index: 3846959 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 4158813 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5662. Min Act: -0.1700
Data Index: 714953 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5975. Min Act: -0.1700
Data Index: 5090579 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5662. Min Act: -0.1700
Data Index: 2624285 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5662. Min Act: -0.1700
Data Index: 8005305 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5037. Min Act: -0.1700
Data Index: 3252265 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6490042 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 714956 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 285609 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 5395755 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 1535224 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 4445931 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 4445934 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 5389584 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 4884095 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 2345672 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 4445930 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5350. Min Act: -0.1700
Data Index: 4772624 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5975. Min Range: -4.5975
Max Act: 4.5037. Min Act: -0.1700
Data Index: 4513026 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19