Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 549 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3936. Min Range: -5.3936
Max Act: 5.3936. Min Act: -0.1700
Data Index: 8606194 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.9873. Min Act: -0.1700
Data Index: 5286626 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.9561. Min Act: -0.1700
Data Index: 5064620 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.9248. Min Act: -0.1700
Data Index: 3532712 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.9561. Min Act: -0.1700
Data Index: 7829166 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8936. Min Act: -0.1700
Data Index: 3355344 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8936. Min Act: -0.1700
Data Index: 5406998 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8311. Min Act: -0.1700
Data Index: 190674 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8311. Min Act: -0.1700
Data Index: 2357706 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8311. Min Act: -0.1700
Data Index: 8636116 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8311. Min Act: -0.1700
Data Index: 5016096 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.8311. Min Act: -0.1700
Data Index: 7457191 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7998. Min Act: -0.1700
Data Index: 185340 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7998. Min Act: -0.1700
Data Index: 8277755 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7998. Min Act: -0.1700
Data Index: 1838401 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7686. Min Act: -0.1700
Data Index: 7908612 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7686. Min Act: -0.1700
Data Index: 2747215 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7686. Min Act: -0.1700
Data Index: 4131515 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7686. Min Act: -0.1700
Data Index: 2784166 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3936. Min Range: -5.3936
Max Act: 4.7686. Min Act: -0.1700
Data Index: 6016715 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19