Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2744 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3786. Min Act: -0.1700
Data Index: 7733910 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3472. Min Act: -0.1700
Data Index: 3473033 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3315. Min Act: -0.1700
Data Index: 3439050 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3315. Min Act: -0.1700
Data Index: 8306062 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3315. Min Act: -0.1700
Data Index: 7090781 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3158. Min Act: -0.1700
Data Index: 3240738 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.3001. Min Act: -0.1700
Data Index: 1258445 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2687. Min Act: -0.1700
Data Index: 3907801 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2687. Min Act: -0.1700
Data Index: 656820 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2216. Min Act: -0.1700
Data Index: 3506022 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2373. Min Act: -0.1700
Data Index: 1262872 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2216. Min Act: -0.1700
Data Index: 503303 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2216. Min Act: -0.1700
Data Index: 8177393 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2373. Min Act: -0.1700
Data Index: 4930890 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2059. Min Act: -0.1700
Data Index: 8150608 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.1901. Min Act: -0.1700
Data Index: 4755822 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.1744. Min Act: -0.1700
Data Index: 7187144 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.1744. Min Act: -0.1700
Data Index: 7008329 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.2059. Min Act: -0.1700
Data Index: 2761077 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3786. Min Range: -3.3786
Max Act: 3.1744. Min Act: -0.1700
Data Index: 5483700 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19