Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5399 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.6869. Min Act: -0.1700
Data Index: 2017224 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.5306. Min Act: -0.1700
Data Index: 3282287 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.3119. Min Act: -0.1700
Data Index: 3714137 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.2494. Min Act: -0.1700
Data Index: 5705420 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.2181. Min Act: -0.1700
Data Index: 3830723 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.1556. Min Act: -0.1700
Data Index: 1766145 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.1244. Min Act: -0.1700
Data Index: 3996474 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.1244. Min Act: -0.1700
Data Index: 8568009 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.0931. Min Act: -0.1700
Data Index: 4308280 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.0931. Min Act: -0.1700
Data Index: 616937 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.0931. Min Act: -0.1700
Data Index: 940024 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.0931. Min Act: -0.1700
Data Index: 1624687 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9994. Min Act: -0.1700
Data Index: 4780105 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9994. Min Act: -0.1700
Data Index: 4368283 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9994. Min Act: -0.1700
Data Index: 384647 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6869. Min Range: -5.6869
Max Act: 5.0306. Min Act: -0.1700
Data Index: 8553330 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9994. Min Act: -0.1700
Data Index: 6209794 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9681. Min Act: -0.1700
Data Index: 1512312 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9681. Min Act: -0.1700
Data Index: 770568 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6869. Min Range: -5.6869
Max Act: 4.9681. Min Act: -0.1700
Data Index: 654801 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19