Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.5835. Min Act: -0.1700
Data Index: 2653736 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.5210. Min Act: -0.1700
Data Index: 6380016 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4585. Min Act: -0.1700
Data Index: 618754 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4585. Min Act: -0.1700
Data Index: 145445 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 97777 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 8809631 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 683559 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 6366551 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 3618216 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 8279570 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 7478592 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3960. Min Act: -0.1700
Data Index: 7088336 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 4169217 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.4272. Min Act: -0.1700
Data Index: 683558 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3960. Min Act: -0.1700
Data Index: 8547499 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3960. Min Act: -0.1700
Data Index: 7032439 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3960. Min Act: -0.1700
Data Index: 1257277 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3647. Min Act: -0.1700
Data Index: 2061369 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3647. Min Act: -0.1700
Data Index: 4834795 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5835. Min Range: -5.5835
Max Act: 5.3647. Min Act: -0.1700
Data Index: 5790834 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19