Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1965 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.6136. Min Act: -0.1700
Data Index: 5262530 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.5198. Min Act: -0.1700
Data Index: 1983325 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4573. Min Act: -0.1700
Data Index: 4027986 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4573. Min Act: -0.1700
Data Index: 7761734 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.4261. Min Act: -0.1700
Data Index: 2294436 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3948. Min Act: -0.1700
Data Index: 694110 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3948. Min Act: -0.1700
Data Index: 4046275 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3323. Min Act: -0.1700
Data Index: 866687 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 4478952 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 3041481 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.3011. Min Act: -0.1700
Data Index: 1099295 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2698. Min Act: -0.1700
Data Index: 1694950 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 6800821 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 4212665 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 2763123 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 740151 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 6001125 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 392870 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2386. Min Act: -0.1700
Data Index: 1340415 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6136. Min Range: -4.6136
Max Act: 4.2073. Min Act: -0.1700
Data Index: 3338828 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19