Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0871. Min Range: -8.0871
Max Act: 8.0871. Min Act: -0.1700
Data Index: 7096678 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.8996. Min Act: -0.1700
Data Index: 2862237 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.8371. Min Act: -0.1700
Data Index: 2104844 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.7746. Min Act: -0.1700
Data Index: 7010116 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.7746. Min Act: -0.1700
Data Index: 8282183 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.6184. Min Act: -0.1700
Data Index: 3507314 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.6496. Min Act: -0.1700
Data Index: 4047833 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.6184. Min Act: -0.1700
Data Index: 3846579 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5871. Min Act: -0.1700
Data Index: 8804748 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5559. Min Act: -0.1700
Data Index: 7844648 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5559. Min Act: -0.1700
Data Index: 2751001 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5559. Min Act: -0.1700
Data Index: 6393450 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5559. Min Act: -0.1700
Data Index: 5807940 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5246. Min Act: -0.1700
Data Index: 6508741 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.5246. Min Act: -0.1700
Data Index: 1991155 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.4934. Min Act: -0.1700
Data Index: 4973446 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.4934. Min Act: -0.1700
Data Index: 8090710 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.4309. Min Act: -0.1700
Data Index: 2917843 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.4621. Min Act: -0.1700
Data Index: 4463168 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0871. Min Range: -8.0871
Max Act: 7.4621. Min Act: -0.1700
Data Index: 277914 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #19