Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4951 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.4042. Min Act: -0.1700
Data Index: 7291238 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.2167. Min Act: -0.1700
Data Index: 7925211 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.2167. Min Act: -0.1700
Data Index: 1179335 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.2167. Min Act: -0.1700
Data Index: 7589949 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.1542. Min Act: -0.1700
Data Index: 1719432 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.1229. Min Act: -0.1700
Data Index: 4025421 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.0604. Min Act: -0.1700
Data Index: 6242087 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.0917. Min Act: -0.1700
Data Index: 169016 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.0917. Min Act: -0.1700
Data Index: 7293033 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.0604. Min Act: -0.1700
Data Index: 4619969 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.0604. Min Act: -0.1700
Data Index: 557217 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4042. Min Range: -8.4042
Max Act: 8.0604. Min Act: -0.1700
Data Index: 8346937 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.9979. Min Act: -0.1700
Data Index: 6932599 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.8729. Min Act: -0.1700
Data Index: 2335429 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.9042. Min Act: -0.1700
Data Index: 5863281 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.8417. Min Act: -0.1700
Data Index: 7730431 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.7792. Min Act: -0.1700
Data Index: 6064104 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.7479. Min Act: -0.1700
Data Index: 619717 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.7792. Min Act: -0.1700
Data Index: 3276444 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4042. Min Range: -8.4042
Max Act: 7.7479. Min Act: -0.1700
Data Index: 393549 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19