Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 139 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.1761. Min Act: -0.1700
Data Index: 7280230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.1449. Min Act: -0.1700
Data Index: 1276911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 2805812 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 8572842 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 5870640 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 2154710 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 2074156 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 8786256 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 8545250 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 8262793 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 711241 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 7825214 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 7098249 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 7098243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0511. Min Act: -0.1700
Data Index: 6246470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0199. Min Act: -0.1700
Data Index: 4494046 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0199. Min Act: -0.1700
Data Index: 4566429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0199. Min Act: -0.1700
Data Index: 4624817 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0199. Min Act: -0.1700
Data Index: 4703707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1761. Min Range: -5.1761
Max Act: 5.0199. Min Act: -0.1700
Data Index: 2170296 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19