Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 796 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.4491. Min Act: -0.1700
Data Index: 4029664 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.3866. Min Act: -0.1700
Data Index: 7310120 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.2616. Min Act: -0.1700
Data Index: 8333983 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.2303. Min Act: -0.1700
Data Index: 7165406 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.2303. Min Act: -0.1700
Data Index: 7165416 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.1991. Min Act: -0.1700
Data Index: 4029666 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.1053. Min Act: -0.1700
Data Index: 1603184 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.0741. Min Act: -0.1700
Data Index: 675390 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.0116. Min Act: -0.1700
Data Index: 2185824 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4491. Min Range: -7.4491
Max Act: 7.0116. Min Act: -0.1700
Data Index: 7867538 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.9491. Min Act: -0.1700
Data Index: 788669 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.9491. Min Act: -0.1700
Data Index: 1985678 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.8866. Min Act: -0.1700
Data Index: 4642898 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.8553. Min Act: -0.1700
Data Index: 28546 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.8866. Min Act: -0.1700
Data Index: 1412821 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.8241. Min Act: -0.1700
Data Index: 1944896 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.8241. Min Act: -0.1700
Data Index: 4108012 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.7928. Min Act: -0.1700
Data Index: 5148077 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.7928. Min Act: -0.1700
Data Index: 8653831 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4491. Min Range: -7.4491
Max Act: 6.7616. Min Act: -0.1700
Data Index: 4144250 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19