Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.4620. Min Act: -0.1700
Data Index: 5134266 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3995. Min Act: -0.1700
Data Index: 3665683 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3370. Min Act: -0.1700
Data Index: 6581841 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3057. Min Act: -0.1700
Data Index: 3001527 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3057. Min Act: -0.1700
Data Index: 8407350 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3682. Min Act: -0.1700
Data Index: 7713823 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3057. Min Act: -0.1700
Data Index: 1010459 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2745. Min Act: -0.1700
Data Index: 4673900 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3057. Min Act: -0.1700
Data Index: 2262824 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 2847714 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 6825198 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2745. Min Act: -0.1700
Data Index: 6768577 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2745. Min Act: -0.1700
Data Index: 2016054 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.3057. Min Act: -0.1700
Data Index: 61548 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 7742546 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 523212 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 3363225 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 753012 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 763334 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4620. Min Range: -4.4620
Max Act: 4.2432. Min Act: -0.1700
Data Index: 263392 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19