Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.5028. Min Act: -0.1700
Data Index: 2748559 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.3775. Min Act: -0.1700
Data Index: 2048335 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.3618. Min Act: -0.1700
Data Index: 7620981 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.3461. Min Act: -0.1700
Data Index: 4998388 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2990. Min Act: -0.1700
Data Index: 4781582 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2990. Min Act: -0.1700
Data Index: 6839911 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2990. Min Act: -0.1700
Data Index: 2502998 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2519. Min Act: -0.1700
Data Index: 4122051 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2362. Min Act: -0.1700
Data Index: 7942736 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2205. Min Act: -0.1700
Data Index: 1467603 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.2205. Min Act: -0.1700
Data Index: 1706404 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1890. Min Act: -0.1700
Data Index: 8475359 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1733. Min Act: -0.1700
Data Index: 3789404 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1733. Min Act: -0.1700
Data Index: 6023106 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1418. Min Act: -0.1700
Data Index: 4925289 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1260. Min Act: -0.1700
Data Index: 4809573 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1260. Min Act: -0.1700
Data Index: 7194873 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1260. Min Act: -0.1700
Data Index: 523566 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1103. Min Act: -0.1700
Data Index: 5649704 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5028. Min Range: -3.5028
Max Act: 3.1260. Min Act: -0.1700
Data Index: 6021462 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19