Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.8543. Min Act: -0.1700
Data Index: 1360888 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.5418. Min Act: -0.1700
Data Index: 8643288 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.4793. Min Act: -0.1700
Data Index: 1637718 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.4793. Min Act: -0.1700
Data Index: 6848311 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.5105. Min Act: -0.1700
Data Index: 8314933 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.4480. Min Act: -0.1700
Data Index: 2707102 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.3855. Min Act: -0.1700
Data Index: 3315333 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.3230. Min Act: -0.1700
Data Index: 1639328 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.3855. Min Act: -0.1700
Data Index: 3687587 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.2918. Min Act: -0.1700
Data Index: 1547832 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.2605. Min Act: -0.1700
Data Index: 4938298 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.2293. Min Act: -0.1700
Data Index: 7543382 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1980. Min Act: -0.1700
Data Index: 3945017 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1980. Min Act: -0.1700
Data Index: 8690057 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1668. Min Act: -0.1700
Data Index: 735836 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1980. Min Act: -0.1700
Data Index: 4219971 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1043. Min Act: -0.1700
Data Index: 1754886 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1043. Min Act: -0.1700
Data Index: 2161983 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.1355. Min Act: -0.1700
Data Index: 1556636 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8543. Min Range: -7.8543
Max Act: 7.0730. Min Act: -0.1700
Data Index: 3858393 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19