Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.5793. Min Act: -0.1700
Data Index: 5891684 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.3293. Min Act: -0.1700
Data Index: 3515975 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.3293. Min Act: -0.1700
Data Index: 3588280 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.2668. Min Act: -0.1700
Data Index: 397905 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.2355. Min Act: -0.1700
Data Index: 3865006 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.2043. Min Act: -0.1700
Data Index: 6850372 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.2043. Min Act: -0.1700
Data Index: 8114235 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.2043. Min Act: -0.1700
Data Index: 1223756 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1730. Min Act: -0.1700
Data Index: 8029862 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1730. Min Act: -0.1700
Data Index: 2420816 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.2043. Min Act: -0.1700
Data Index: 4016997 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1730. Min Act: -0.1700
Data Index: 7439723 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1418. Min Act: -0.1700
Data Index: 446359 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1418. Min Act: -0.1700
Data Index: 421015 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1730. Min Act: -0.1700
Data Index: 3504945 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1730. Min Act: -0.1700
Data Index: 4770425 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1105. Min Act: -0.1700
Data Index: 5562955 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1105. Min Act: -0.1700
Data Index: 3805671 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1105. Min Act: -0.1700
Data Index: 3420629 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5793. Min Range: -4.5793
Max Act: 4.1105. Min Act: -0.1700
Data Index: 4314789 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19