Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 549 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4510. Min Range: -7.4510
Max Act: 7.4510. Min Act: -0.1700
Data Index: 7965132 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4510. Min Range: -7.4510
Max Act: 7.2323. Min Act: -0.1700
Data Index: 8336682 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4510. Min Range: -7.4510
Max Act: 7.0135. Min Act: -0.1700
Data Index: 8408857 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4510. Min Range: -7.4510
Max Act: 7.0135. Min Act: -0.1700
Data Index: 8808239 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.8885. Min Act: -0.1700
Data Index: 6332910 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.8573. Min Act: -0.1700
Data Index: 5938781 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7948. Min Act: -0.1700
Data Index: 4168304 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7948. Min Act: -0.1700
Data Index: 197431 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7635. Min Act: -0.1700
Data Index: 3709820 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7635. Min Act: -0.1700
Data Index: 7255571 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7635. Min Act: -0.1700
Data Index: 7893927 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5975568 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7010. Min Act: -0.1700
Data Index: 6806523 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7010. Min Act: -0.1700
Data Index: 948208 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.7010. Min Act: -0.1700
Data Index: 3911718 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.6698. Min Act: -0.1700
Data Index: 700688 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.6385. Min Act: -0.1700
Data Index: 2525450 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.6385. Min Act: -0.1700
Data Index: 5147169 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.5448. Min Act: -0.1700
Data Index: 8751808 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4510. Min Range: -7.4510
Max Act: 6.5760. Min Act: -0.1700
Data Index: 2785184 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19