Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6309. Min Range: -7.6309
Max Act: 7.6309. Min Act: -0.1700
Data Index: 1981160 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6309. Min Range: -7.6309
Max Act: 7.5997. Min Act: -0.1700
Data Index: 4883680 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6309. Min Range: -7.6309
Max Act: 7.5684. Min Act: -0.1700
Data Index: 7150925 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6309. Min Range: -7.6309
Max Act: 7.2559. Min Act: -0.1700
Data Index: 3843562 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6309. Min Range: -7.6309
Max Act: 7.2247. Min Act: -0.1700
Data Index: 5018136 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6309. Min Range: -7.6309
Max Act: 7.1309. Min Act: -0.1700
Data Index: 3802679 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.9747. Min Act: -0.1700
Data Index: 5034554 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.9122. Min Act: -0.1700
Data Index: 736284 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.8497. Min Act: -0.1700
Data Index: 4917425 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.8809. Min Act: -0.1700
Data Index: 748333 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.8497. Min Act: -0.1700
Data Index: 2122468 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.7247. Min Act: -0.1700
Data Index: 638554 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.7247. Min Act: -0.1700
Data Index: 5920749 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.7247. Min Act: -0.1700
Data Index: 4328902 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.7247. Min Act: -0.1700
Data Index: 1023926 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.6934. Min Act: -0.1700
Data Index: 1335774 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.6934. Min Act: -0.1700
Data Index: 5505094 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.6934. Min Act: -0.1700
Data Index: 1675961 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.6934. Min Act: -0.1700
Data Index: 642456 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6309. Min Range: -7.6309
Max Act: 6.6934. Min Act: -0.1700
Data Index: 2780520 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19