Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0890. Min Range: -4.0890
Max Act: 4.0890. Min Act: -0.1700
Data Index: 3581977 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0890. Min Range: -4.0890
Max Act: 4.0890. Min Act: -0.1700
Data Index: 6837318 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0890. Min Range: -4.0890
Max Act: 4.0577. Min Act: -0.1700
Data Index: 7324017 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0890. Min Range: -4.0890
Max Act: 4.0577. Min Act: -0.1700
Data Index: 4648992 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.9952. Min Act: -0.1700
Data Index: 113438 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.9327. Min Act: -0.1700
Data Index: 2153303 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.9327. Min Act: -0.1700
Data Index: 5489708 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8702. Min Act: -0.1700
Data Index: 323206 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8389. Min Act: -0.1700
Data Index: 7702534 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8389. Min Act: -0.1700
Data Index: 1083244 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8389. Min Act: -0.1700
Data Index: 43272 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8389. Min Act: -0.1700
Data Index: 3004127 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8389. Min Act: -0.1700
Data Index: 1330694 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8702. Min Act: -0.1700
Data Index: 2958717 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8389. Min Act: -0.1700
Data Index: 2815728 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8076. Min Act: -0.1700
Data Index: 5112959 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8076. Min Act: -0.1700
Data Index: 6740742 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.7763. Min Act: -0.1700
Data Index: 6938108 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8076. Min Act: -0.1700
Data Index: 5892209 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0890. Min Range: -4.0890
Max Act: 3.8076. Min Act: -0.1700
Data Index: 571694 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19