Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.9032. Min Act: -0.1700
Data Index: 6552822 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.2470. Min Act: -0.1700
Data Index: 3394685 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.1220. Min Act: -0.1700
Data Index: 3900569 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.0907. Min Act: -0.1700
Data Index: 703420 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.0595. Min Act: -0.1700
Data Index: 852145 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.0282. Min Act: -0.1700
Data Index: 7747986 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9032. Min Range: -5.9032
Max Act: 5.0282. Min Act: -0.1700
Data Index: 8100167 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9970. Min Act: -0.1700
Data Index: 3705062 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9657. Min Act: -0.1700
Data Index: 1448851 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9657. Min Act: -0.1700
Data Index: 5333951 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9657. Min Act: -0.1700
Data Index: 438054 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9657. Min Act: -0.1700
Data Index: 379819 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9345. Min Act: -0.1700
Data Index: 7958036 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9657. Min Act: -0.1700
Data Index: 7829155 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9032. Min Act: -0.1700
Data Index: 4481246 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.8720. Min Act: -0.1700
Data Index: 7739123 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.9032. Min Act: -0.1700
Data Index: 6722555 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.8720. Min Act: -0.1700
Data Index: 5159984 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.8720. Min Act: -0.1700
Data Index: 3099457 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9032. Min Range: -5.9032
Max Act: 4.8407. Min Act: -0.1700
Data Index: 3435012 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19