Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.1281. Min Act: -0.1700
Data Index: 273568 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0969. Min Act: -0.1700
Data Index: 806801 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0344. Min Act: -0.1700
Data Index: 310294 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0344. Min Act: -0.1700
Data Index: 839604 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0344. Min Act: -0.1700
Data Index: 6878224 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0344. Min Act: -0.1700
Data Index: 6143916 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0031. Min Act: -0.1700
Data Index: 5564182 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0344. Min Act: -0.1700
Data Index: 5741788 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0031. Min Act: -0.1700
Data Index: 8565835 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1281. Min Range: -4.1281
Max Act: 4.0031. Min Act: -0.1700
Data Index: 3380881 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9719. Min Act: -0.1700
Data Index: 4381290 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9719. Min Act: -0.1700
Data Index: 2128245 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9719. Min Act: -0.1700
Data Index: 8366436 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9719. Min Act: -0.1700
Data Index: 7400356 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9406. Min Act: -0.1700
Data Index: 4900779 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9093. Min Act: -0.1700
Data Index: 65655 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9406. Min Act: -0.1700
Data Index: 2945128 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9406. Min Act: -0.1700
Data Index: 3001258 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9406. Min Act: -0.1700
Data Index: 4619628 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1281. Min Range: -4.1281
Max Act: 3.9406. Min Act: -0.1700
Data Index: 648608 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19