Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5185 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0795. Min Range: -1.0795
Max Act: 1.0795. Min Act: -0.1683
Data Index: 3367340 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0795. Min Range: -1.0795
Max Act: 1.0446. Min Act: -0.1686
Data Index: 7967735 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0795. Min Range: -1.0795
Max Act: 1.0185. Min Act: -0.1700
Data Index: 7344852 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9838. Min Act: -0.1699
Data Index: 8023176 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9924. Min Act: -0.1700
Data Index: 2846503 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9665. Min Act: -0.1700
Data Index: 7426832 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9751. Min Act: -0.1700
Data Index: 6553562 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1698
Data Index: 2064281 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1700
Data Index: 1238577 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1692
Data Index: 4941958 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9665. Min Act: -0.1700
Data Index: 4311795 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1699
Data Index: 390264 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9665. Min Act: -0.1699
Data Index: 7017020 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1700
Data Index: 8515175 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1700
Data Index: 7692764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9492. Min Act: -0.1700
Data Index: 7809339 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1700
Data Index: 4026592 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1700
Data Index: 215159 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1698
Data Index: 1993104 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0795. Min Range: -1.0795
Max Act: 0.9578. Min Act: -0.1700
Data Index: 2858567 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19