Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.6309. Min Act: -0.1700
Data Index: 399283 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.5684. Min Act: -0.1700
Data Index: 3245004 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.5059. Min Act: -0.1700
Data Index: 4167878 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.4747. Min Act: -0.1700
Data Index: 6530432 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.4122. Min Act: -0.1700
Data Index: 961225 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.4434. Min Act: -0.1700
Data Index: 4918061 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.4122. Min Act: -0.1700
Data Index: 2073935 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.4122. Min Act: -0.1700
Data Index: 4850018 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.3497. Min Act: -0.1700
Data Index: 4384642 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.3184. Min Act: -0.1700
Data Index: 157005 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.3497. Min Act: -0.1700
Data Index: 8193603 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.2872. Min Act: -0.1700
Data Index: 3264493 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.2559. Min Act: -0.1700
Data Index: 5950106 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.2559. Min Act: -0.1700
Data Index: 555142 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.2559. Min Act: -0.1700
Data Index: 3316461 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.2247. Min Act: -0.1700
Data Index: 140641 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.2247. Min Act: -0.1700
Data Index: 4832384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.1934. Min Act: -0.1700
Data Index: 4679191 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.1934. Min Act: -0.1700
Data Index: 2843257 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6309. Min Range: -6.6309
Max Act: 6.1622. Min Act: -0.1700
Data Index: 7227280 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19