Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 397 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.4431. Min Act: -0.1700
Data Index: 5583806 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.4118. Min Act: -0.1700
Data Index: 1620779 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.3806. Min Act: -0.1700
Data Index: 4642847 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.1931. Min Act: -0.1700
Data Index: 2633881 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.1618. Min Act: -0.1700
Data Index: 7323151 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.1306. Min Act: -0.1700
Data Index: 5352962 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0993. Min Act: -0.1700
Data Index: 3674865 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0993. Min Act: -0.1700
Data Index: 1479177 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0368. Min Act: -0.1700
Data Index: 7139980 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0368. Min Act: -0.1700
Data Index: 3423962 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0368. Min Act: -0.1700
Data Index: 7611414 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0056. Min Act: -0.1700
Data Index: 5649015 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0056. Min Act: -0.1700
Data Index: 7179389 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0056. Min Act: -0.1700
Data Index: 5139568 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4431. Min Range: -5.4431
Max Act: 5.0056. Min Act: -0.1700
Data Index: 2581093 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4431. Min Range: -5.4431
Max Act: 4.9743. Min Act: -0.1700
Data Index: 5558943 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4431. Min Range: -5.4431
Max Act: 4.9743. Min Act: -0.1700
Data Index: 4247160 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4431. Min Range: -5.4431
Max Act: 4.9743. Min Act: -0.1700
Data Index: 8222412 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4431. Min Range: -5.4431
Max Act: 4.9743. Min Act: -0.1700
Data Index: 7121746 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4431. Min Range: -5.4431
Max Act: 4.9743. Min Act: -0.1700
Data Index: 8696729 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19