Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.2785. Min Act: -0.1700
Data Index: 5102585 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.2785. Min Act: -0.1700
Data Index: 5333227 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1848. Min Act: -0.1700
Data Index: 6588921 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1848. Min Act: -0.1700
Data Index: 6975821 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1223. Min Act: -0.1700
Data Index: 8509556 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.2160. Min Act: -0.1700
Data Index: 466230 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.1535. Min Act: -0.1700
Data Index: 6143826 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0910. Min Act: -0.1700
Data Index: 6730662 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0910. Min Act: -0.1700
Data Index: 4027820 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0598. Min Act: -0.1700
Data Index: 3721379 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9973. Min Act: -0.1700
Data Index: 3441467 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0598. Min Act: -0.1700
Data Index: 2551642 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0285. Min Act: -0.1700
Data Index: 863592 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0598. Min Act: -0.1700
Data Index: 5670796 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0285. Min Act: -0.1700
Data Index: 7187907 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9973. Min Act: -0.1700
Data Index: 4311671 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0598. Min Act: -0.1700
Data Index: 2924089 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9973. Min Act: -0.1700
Data Index: 5866945 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2785. Min Range: -8.2785
Max Act: 8.0285. Min Act: -0.1700
Data Index: 7699406 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2785. Min Range: -8.2785
Max Act: 7.9973. Min Act: -0.1700
Data Index: 6347247 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19