Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2067 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7585. Min Act: -0.1700
Data Index: 3162786 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7585. Min Act: -0.1700
Data Index: 4836796 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7898. Min Act: -0.1700
Data Index: 5296627 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7585. Min Act: -0.1700
Data Index: 621758 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7585. Min Act: -0.1700
Data Index: 3597543 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 2033172 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 1512537 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 2026149 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 8231227 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 7047225 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 6563461 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 5793972 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 4515647 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.6960. Min Act: -0.1700
Data Index: 2630314 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 2689786 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.6960. Min Act: -0.1700
Data Index: 1078316 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.6960. Min Act: -0.1700
Data Index: 1298516 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.7273. Min Act: -0.1700
Data Index: 3040632 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.6960. Min Act: -0.1700
Data Index: 3140707 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7898. Min Range: -3.7898
Max Act: 3.6960. Min Act: -0.1700
Data Index: 1410655 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19