Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1291. Min Range: -4.1291
Max Act: 4.1291. Min Act: -0.1700
Data Index: 1315084 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.9728. Min Act: -0.1700
Data Index: 7589303 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.9728. Min Act: -0.1700
Data Index: 8001399 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.8164. Min Act: -0.1700
Data Index: 5112936 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.8477. Min Act: -0.1700
Data Index: 6084635 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.8164. Min Act: -0.1700
Data Index: 8341331 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.8164. Min Act: -0.1700
Data Index: 7284453 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.8164. Min Act: -0.1700
Data Index: 1305817 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7852. Min Act: -0.1700
Data Index: 3619747 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7852. Min Act: -0.1700
Data Index: 3884821 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7852. Min Act: -0.1700
Data Index: 3589171 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7539. Min Act: -0.1700
Data Index: 3628759 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7539. Min Act: -0.1700
Data Index: 5598886 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7852. Min Act: -0.1700
Data Index: 8584062 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7852. Min Act: -0.1700
Data Index: 8214420 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7539. Min Act: -0.1700
Data Index: 5459747 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7226. Min Act: -0.1700
Data Index: 8341332 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7382. Min Act: -0.1700
Data Index: 3199450 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.7226. Min Act: -0.1700
Data Index: 2831744 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1291. Min Range: -4.1291
Max Act: 3.6913. Min Act: -0.1700
Data Index: 1370622 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19