Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2682. Min Act: -0.1700
Data Index: 390415 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.2369. Min Act: -0.1700
Data Index: 45241 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1432. Min Act: -0.1700
Data Index: 8003888 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1119. Min Act: -0.1700
Data Index: 2591228 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.1119. Min Act: -0.1700
Data Index: 8200748 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0807. Min Act: -0.1700
Data Index: 1293684 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0494. Min Act: -0.1700
Data Index: 4265475 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0494. Min Act: -0.1700
Data Index: 7974309 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 6847755 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 2105115 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2682. Min Range: -5.2682
Max Act: 5.0182. Min Act: -0.1700
Data Index: 3035074 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 6419737 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9557. Min Act: -0.1700
Data Index: 6476947 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9869. Min Act: -0.1700
Data Index: 772052 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9244. Min Act: -0.1700
Data Index: 5722991 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.9244. Min Act: -0.1700
Data Index: 4808564 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8619. Min Act: -0.1700
Data Index: 3035073 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8932. Min Act: -0.1700
Data Index: 7484344 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8932. Min Act: -0.1700
Data Index: 1603827 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2682. Min Range: -5.2682
Max Act: 4.8932. Min Act: -0.1700
Data Index: 5385425 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19