Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.5080. Min Act: -0.1700
Data Index: 4434624 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.5080. Min Act: -0.1700
Data Index: 4875163 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.4767. Min Act: -0.1700
Data Index: 3105280 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.3830. Min Act: -0.1700
Data Index: 6570945 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.3205. Min Act: -0.1700
Data Index: 6128062 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.3205. Min Act: -0.1700
Data Index: 840288 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.2580. Min Act: -0.1700
Data Index: 4700213 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.2580. Min Act: -0.1700
Data Index: 228299 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.2267. Min Act: -0.1700
Data Index: 8549975 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.2267. Min Act: -0.1700
Data Index: 5222321 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1955. Min Act: -0.1700
Data Index: 1179196 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1955. Min Act: -0.1700
Data Index: 2920634 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1642. Min Act: -0.1700
Data Index: 5167493 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1330. Min Act: -0.1700
Data Index: 8204541 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1642. Min Act: -0.1700
Data Index: 7266070 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1955. Min Act: -0.1700
Data Index: 6189757 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1017. Min Act: -0.1700
Data Index: 6762838 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1017. Min Act: -0.1700
Data Index: 1247606 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1017. Min Act: -0.1700
Data Index: 6082656 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5080. Min Range: -5.5080
Max Act: 5.1017. Min Act: -0.1700
Data Index: 6182774 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19