Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3183 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.8081. Min Act: -0.1700
Data Index: 8796323 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6830. Min Act: -0.1700
Data Index: 5052224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6517. Min Act: -0.1700
Data Index: 3948698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6517. Min Act: -0.1700
Data Index: 7265022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6517. Min Act: -0.1700
Data Index: 2591920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6517. Min Act: -0.1700
Data Index: 8220257 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6517. Min Act: -0.1700
Data Index: 4770794 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6204. Min Act: -0.1700
Data Index: 7701285 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6204. Min Act: -0.1700
Data Index: 238378 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6204. Min Act: -0.1700
Data Index: 6355391 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.6204. Min Act: -0.1700
Data Index: 56944 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5891. Min Act: -0.1700
Data Index: 7459176 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5578. Min Act: -0.1700
Data Index: 1133071 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5578. Min Act: -0.1700
Data Index: 7977076 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5578. Min Act: -0.1700
Data Index: 7286703 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.5578. Min Act: -0.1700
Data Index: 617847 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.4951. Min Act: -0.1700
Data Index: 812694 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.4638. Min Act: -0.1700
Data Index: 137969 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.4638. Min Act: -0.1700
Data Index: 3051658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8081. Min Range: -3.8081
Max Act: 3.4638. Min Act: -0.1700
Data Index: 3591835 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19