Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6020 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.3593. Min Act: -0.1700
Data Index: 2144053 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.2968. Min Act: -0.1700
Data Index: 7254944 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.2655. Min Act: -0.1700
Data Index: 7948733 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.1405. Min Act: -0.1700
Data Index: 7908631 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.1405. Min Act: -0.1700
Data Index: 8398191 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.1405. Min Act: -0.1700
Data Index: 5327983 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.1093. Min Act: -0.1700
Data Index: 2738134 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.0780. Min Act: -0.1700
Data Index: 4298950 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.0468. Min Act: -0.1700
Data Index: 7117966 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.0155. Min Act: -0.1700
Data Index: 6884149 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.0155. Min Act: -0.1700
Data Index: 3100795 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3593. Min Range: -6.3593
Max Act: 6.0155. Min Act: -0.1700
Data Index: 7948739 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9843. Min Act: -0.1700
Data Index: 4596729 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9843. Min Act: -0.1700
Data Index: 5796487 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9530. Min Act: -0.1700
Data Index: 7948735 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9530. Min Act: -0.1700
Data Index: 3880074 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9218. Min Act: -0.1700
Data Index: 5412063 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1161682 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1015733 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3593. Min Range: -6.3593
Max Act: 5.9218. Min Act: -0.1700
Data Index: 1292033 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19