Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1991 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1949. Min Range: -7.1949
Max Act: 7.1949. Min Act: -0.1700
Data Index: 7699451 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.9762. Min Act: -0.1700
Data Index: 8579613 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.7887. Min Act: -0.1700
Data Index: 385489 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.7262. Min Act: -0.1700
Data Index: 2646235 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.7262. Min Act: -0.1700
Data Index: 8801487 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.6949. Min Act: -0.1700
Data Index: 6532652 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.6637. Min Act: -0.1700
Data Index: 3456577 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.6637. Min Act: -0.1700
Data Index: 2717115 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.6637. Min Act: -0.1700
Data Index: 8321869 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.5699. Min Act: -0.1700
Data Index: 4327250 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.5387. Min Act: -0.1700
Data Index: 3253454 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4762. Min Act: -0.1700
Data Index: 3810861 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4762. Min Act: -0.1700
Data Index: 8453427 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4762. Min Act: -0.1700
Data Index: 1092014 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4762. Min Act: -0.1700
Data Index: 5232351 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4762. Min Act: -0.1700
Data Index: 1605080 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4449. Min Act: -0.1700
Data Index: 259391 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4449. Min Act: -0.1700
Data Index: 8133487 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4449. Min Act: -0.1700
Data Index: 5199170 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1949. Min Range: -7.1949
Max Act: 6.4449. Min Act: -0.1700
Data Index: 6389622 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19