Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5244 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.6073. Min Act: -0.1700
Data Index: 4307362 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.6073. Min Act: -0.1700
Data Index: 4037948 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.5761. Min Act: -0.1700
Data Index: 4443502 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.5448. Min Act: -0.1700
Data Index: 8171314 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.5136. Min Act: -0.1700
Data Index: 6852953 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4823. Min Act: -0.1700
Data Index: 4443503 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4823. Min Act: -0.1700
Data Index: 7657776 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.5136. Min Act: -0.1700
Data Index: 5563470 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4823. Min Act: -0.1700
Data Index: 2209677 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4511. Min Act: -0.1700
Data Index: 492015 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4511. Min Act: -0.1700
Data Index: 7110795 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4511. Min Act: -0.1700
Data Index: 6065078 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4198. Min Act: -0.1700
Data Index: 620490 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4198. Min Act: -0.1700
Data Index: 7005738 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.4198. Min Act: -0.1700
Data Index: 1420528 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.3886. Min Act: -0.1700
Data Index: 6065077 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.3886. Min Act: -0.1700
Data Index: 1049630 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.3886. Min Act: -0.1700
Data Index: 7005750 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.3886. Min Act: -0.1700
Data Index: 219581 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6073. Min Range: -4.6073
Max Act: 4.3573. Min Act: -0.1700
Data Index: 1156524 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19