Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5182 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.3835. Min Act: -0.1700
Data Index: 5282363 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.3522. Min Act: -0.1700
Data Index: 2155325 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.3210. Min Act: -0.1700
Data Index: 2347220 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.2585. Min Act: -0.1700
Data Index: 748563 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.2585. Min Act: -0.1700
Data Index: 4526687 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.2585. Min Act: -0.1700
Data Index: 7665548 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.2585. Min Act: -0.1700
Data Index: 4766564 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 6774716 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 1665441 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 6839637 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 512435 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 434780 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 6967222 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1960. Min Act: -0.1700
Data Index: 4864523 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1647. Min Act: -0.1700
Data Index: 4000643 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1647. Min Act: -0.1700
Data Index: 338104 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1647. Min Act: -0.1700
Data Index: 8698623 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1647. Min Act: -0.1700
Data Index: 3738865 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1647. Min Act: -0.1700
Data Index: 572795 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3835. Min Range: -5.3835
Max Act: 5.1647. Min Act: -0.1700
Data Index: 5379416 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19