Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1911 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.9401. Min Act: -0.1700
Data Index: 624945 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.8151. Min Act: -0.1700
Data Index: 8776316 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.7838. Min Act: -0.1700
Data Index: 6428879 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.7526. Min Act: -0.1700
Data Index: 1135703 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.6901. Min Act: -0.1700
Data Index: 5804999 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.7213. Min Act: -0.1700
Data Index: 4778250 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.6276. Min Act: -0.1700
Data Index: 2692304 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.6276. Min Act: -0.1700
Data Index: 1544408 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.6276. Min Act: -0.1700
Data Index: 5408420 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5963. Min Act: -0.1700
Data Index: 1262763 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5963. Min Act: -0.1700
Data Index: 6887835 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5963. Min Act: -0.1700
Data Index: 2132102 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5963. Min Act: -0.1700
Data Index: 231313 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5963. Min Act: -0.1700
Data Index: 1955891 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5651. Min Act: -0.1700
Data Index: 6269697 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5651. Min Act: -0.1700
Data Index: 8539852 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5651. Min Act: -0.1700
Data Index: 1417584 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5651. Min Act: -0.1700
Data Index: 6254762 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5651. Min Act: -0.1700
Data Index: 4072853 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9401. Min Range: -5.9401
Max Act: 5.5338. Min Act: -0.1700
Data Index: 4492002 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19