Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.4901. Min Act: -0.1700
Data Index: 1946793 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.4901. Min Act: -0.1700
Data Index: 3707152 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.4588. Min Act: -0.1700
Data Index: 5984648 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.4901. Min Act: -0.1700
Data Index: 390224 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.4276. Min Act: -0.1700
Data Index: 3358002 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3338. Min Act: -0.1700
Data Index: 2164596 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3963. Min Act: -0.1700
Data Index: 8064534 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3651. Min Act: -0.1700
Data Index: 6633696 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3338. Min Act: -0.1700
Data Index: 8777111 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3651. Min Act: -0.1700
Data Index: 3637749 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3338. Min Act: -0.1700
Data Index: 4927333 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3026. Min Act: -0.1700
Data Index: 5691059 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3026. Min Act: -0.1700
Data Index: 496982 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3026. Min Act: -0.1700
Data Index: 8069603 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.3026. Min Act: -0.1700
Data Index: 2481556 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.2401. Min Act: -0.1700
Data Index: 837711 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.2401. Min Act: -0.1700
Data Index: 6003509 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.2088. Min Act: -0.1700
Data Index: 7675163 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.2088. Min Act: -0.1700
Data Index: 7030371 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4901. Min Range: -5.4901
Max Act: 5.2088. Min Act: -0.1700
Data Index: 1743040 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19