Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.3987. Min Act: -0.1700
Data Index: 2222557 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.3674. Min Act: -0.1700
Data Index: 3372570 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.3049. Min Act: -0.1700
Data Index: 246183 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.3049. Min Act: -0.1700
Data Index: 1695101 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.3049. Min Act: -0.1700
Data Index: 8420452 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 4136294 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 2226592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 6178634 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 5585468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.3049. Min Act: -0.1700
Data Index: 3551662 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 3942817 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 8138274 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 2162246 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 7353235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2737. Min Act: -0.1700
Data Index: 7004046 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2424. Min Act: -0.1700
Data Index: 6459426 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2424. Min Act: -0.1700
Data Index: 625692 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2424. Min Act: -0.1700
Data Index: 1522644 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2112. Min Act: -0.1700
Data Index: 5847351 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3987. Min Range: -4.3987
Max Act: 4.2112. Min Act: -0.1700
Data Index: 3813630 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19