Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.8411. Min Act: -0.1700
Data Index: 8691311 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7786. Min Act: -0.1700
Data Index: 6577467 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7786. Min Act: -0.1700
Data Index: 939169 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7161. Min Act: -0.1700
Data Index: 6281533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7161. Min Act: -0.1700
Data Index: 7299124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7161. Min Act: -0.1700
Data Index: 7991296 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7161. Min Act: -0.1700
Data Index: 8629816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 4634656 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7161. Min Act: -0.1700
Data Index: 2419501 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.7161. Min Act: -0.1700
Data Index: 1644416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1312471 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 2120607 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 684837 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1966213 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1891440 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1248450 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1300382 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1502138 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 1448272 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8411. Min Range: -5.8411
Max Act: 5.6848. Min Act: -0.1700
Data Index: 393936 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19