Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 958 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.8213. Min Act: -0.1700
Data Index: 1131344 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.8526. Min Act: -0.1700
Data Index: 1925901 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.7588. Min Act: -0.1700
Data Index: 4617863 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.7276. Min Act: -0.1700
Data Index: 2017588 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.6651. Min Act: -0.1700
Data Index: 1778068 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.6338. Min Act: -0.1700
Data Index: 4797793 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5713. Min Act: -0.1700
Data Index: 3566446 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5713. Min Act: -0.1700
Data Index: 6045071 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5713. Min Act: -0.1700
Data Index: 350992 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5401. Min Act: -0.1700
Data Index: 1438609 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5401. Min Act: -0.1700
Data Index: 7189837 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5401. Min Act: -0.1700
Data Index: 4780181 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5088. Min Act: -0.1700
Data Index: 8054556 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5088. Min Act: -0.1700
Data Index: 1192762 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5518617 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5088. Min Act: -0.1700
Data Index: 590773 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.4776. Min Act: -0.1700
Data Index: 5921384 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.4776. Min Act: -0.1700
Data Index: 6376480 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.4776. Min Act: -0.1700
Data Index: 3487749 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8526. Min Range: -5.8526
Max Act: 5.5088. Min Act: -0.1700
Data Index: 4743849 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19