Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3111 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.8888. Min Act: -0.1700
Data Index: 8415943 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.7950. Min Act: -0.1700
Data Index: 4746503 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.7324. Min Act: -0.1700
Data Index: 7381246 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.7168. Min Act: -0.1700
Data Index: 1363812 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.7168. Min Act: -0.1700
Data Index: 3851249 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.6855. Min Act: -0.1700
Data Index: 1363811 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.6855. Min Act: -0.1700
Data Index: 3316133 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.6698. Min Act: -0.1700
Data Index: 7281501 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5916. Min Act: -0.1700
Data Index: 6930314 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.6072. Min Act: -0.1700
Data Index: 3335638 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.6072. Min Act: -0.1700
Data Index: 5253974 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5916. Min Act: -0.1700
Data Index: 3916736 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5759. Min Act: -0.1700
Data Index: 6379557 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5759. Min Act: -0.1700
Data Index: 6037862 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5446. Min Act: -0.1700
Data Index: 2041620 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5446. Min Act: -0.1700
Data Index: 39927 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5290. Min Act: -0.1700
Data Index: 3412035 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5446. Min Act: -0.1700
Data Index: 110677 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5290. Min Act: -0.1700
Data Index: 5718213 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8888. Min Range: -3.8888
Max Act: 3.5133. Min Act: -0.1700
Data Index: 4811314 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19