Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6248 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0737. Min Range: -8.0737
Max Act: 8.0737. Min Act: -0.1700
Data Index: 6210722 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.7612. Min Act: -0.1700
Data Index: 4309795 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.6362. Min Act: -0.1700
Data Index: 3279345 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.5737. Min Act: -0.1700
Data Index: 5921941 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.5737. Min Act: -0.1700
Data Index: 4880407 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.5737. Min Act: -0.1700
Data Index: 7670493 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.5112. Min Act: -0.1700
Data Index: 980411 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.4487. Min Act: -0.1700
Data Index: 5067881 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.3862. Min Act: -0.1700
Data Index: 3294771 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.3237. Min Act: -0.1700
Data Index: 53569 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.3237. Min Act: -0.1700
Data Index: 899617 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.3237. Min Act: -0.1700
Data Index: 6144499 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.3237. Min Act: -0.1700
Data Index: 1094544 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2925. Min Act: -0.1700
Data Index: 1724256 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2925. Min Act: -0.1700
Data Index: 240217 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2612. Min Act: -0.1700
Data Index: 7343086 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2612. Min Act: -0.1700
Data Index: 7617417 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2612. Min Act: -0.1700
Data Index: 4652747 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2925. Min Act: -0.1700
Data Index: 4184813 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0737. Min Range: -8.0737
Max Act: 7.2612. Min Act: -0.1700
Data Index: 5080912 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19