Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4601 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0157. Min Range: -5.0157
Max Act: 5.0157. Min Act: -0.1700
Data Index: 4283125 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.9532. Min Act: -0.1700
Data Index: 1287414 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.9220. Min Act: -0.1700
Data Index: 3577553 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.8595. Min Act: -0.1699
Data Index: 8445920 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.8595. Min Act: -0.1700
Data Index: 3335118 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.8282. Min Act: -0.1700
Data Index: 3900765 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.8282. Min Act: -0.1700
Data Index: 6261998 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7657. Min Act: -0.1700
Data Index: 4262472 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7657. Min Act: -0.1700
Data Index: 3160672 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7345. Min Act: -0.1700
Data Index: 8613051 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7345. Min Act: -0.1700
Data Index: 6021232 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7345. Min Act: -0.1700
Data Index: 8064902 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7032. Min Act: -0.1700
Data Index: 358904 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7032. Min Act: -0.1700
Data Index: 4088817 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7032. Min Act: -0.1700
Data Index: 3652390 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.6720. Min Act: -0.1700
Data Index: 1547112 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.7032. Min Act: -0.1700
Data Index: 7178181 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.6720. Min Act: -0.1700
Data Index: 2142915 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.6720. Min Act: -0.1700
Data Index: 2887609 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0157. Min Range: -5.0157
Max Act: 4.6720. Min Act: -0.1700
Data Index: 8073788 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19