Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0026. Min Range: -8.0026
Max Act: 8.0026. Min Act: -0.1700
Data Index: 2333718 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0026. Min Range: -8.0026
Max Act: 7.0338. Min Act: -0.1700
Data Index: 1348757 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.9401. Min Act: -0.1700
Data Index: 3983348 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.9401. Min Act: -0.1700
Data Index: 3303877 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.8776. Min Act: -0.1700
Data Index: 8362754 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.8463. Min Act: -0.1700
Data Index: 5378688 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.8463. Min Act: -0.1700
Data Index: 5016367 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7838. Min Act: -0.1700
Data Index: 6896501 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7838. Min Act: -0.1700
Data Index: 7318950 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7838. Min Act: -0.1700
Data Index: 7769875 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7526. Min Act: -0.1700
Data Index: 3702302 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7526. Min Act: -0.1700
Data Index: 6894929 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7838. Min Act: -0.1700
Data Index: 7937965 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7526. Min Act: -0.1700
Data Index: 8242874 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7213. Min Act: -0.1700
Data Index: 3163196 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7213. Min Act: -0.1700
Data Index: 5217143 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.7213. Min Act: -0.1700
Data Index: 3263367 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.6901. Min Act: -0.1700
Data Index: 4271566 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.6588. Min Act: -0.1700
Data Index: 474902 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0026. Min Range: -8.0026
Max Act: 6.6588. Min Act: -0.1700
Data Index: 1523169 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19