Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1448 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2781. Min Range: -5.2781
Max Act: 5.2781. Min Act: -0.1700
Data Index: 3984505 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2781. Min Range: -5.2781
Max Act: 5.2781. Min Act: -0.1700
Data Index: 36162 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2781. Min Range: -5.2781
Max Act: 5.1218. Min Act: -0.1700
Data Index: 3560537 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2781. Min Range: -5.2781
Max Act: 5.1218. Min Act: -0.1700
Data Index: 1249068 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2781. Min Range: -5.2781
Max Act: 5.0593. Min Act: -0.1700
Data Index: 8350548 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9968. Min Act: -0.1700
Data Index: 4973933 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9968. Min Act: -0.1700
Data Index: 5039081 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9343. Min Act: -0.1700
Data Index: 3345515 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9343. Min Act: -0.1700
Data Index: 4100875 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9343. Min Act: -0.1700
Data Index: 4101731 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9343. Min Act: -0.1700
Data Index: 6045818 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9031. Min Act: -0.1700
Data Index: 7189442 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.9343. Min Act: -0.1700
Data Index: 8653105 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8718. Min Act: -0.1700
Data Index: 1533698 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8718. Min Act: -0.1700
Data Index: 1155827 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8718. Min Act: -0.1700
Data Index: 7859529 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8718. Min Act: -0.1700
Data Index: 2724309 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8406. Min Act: -0.1700
Data Index: 542198 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8406. Min Act: -0.1700
Data Index: 3586999 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2781. Min Range: -5.2781
Max Act: 4.8406. Min Act: -0.1700
Data Index: 1829990 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19