Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4821 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0229. Min Range: -6.0229
Max Act: 6.0229. Min Act: -0.1700
Data Index: 6064160 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.8354. Min Act: -0.1700
Data Index: 775147 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.7729. Min Act: -0.1700
Data Index: 2095646 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.7416. Min Act: -0.1700
Data Index: 3550588 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.6479. Min Act: -0.1700
Data Index: 2095645 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5854. Min Act: -0.1700
Data Index: 1444844 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5854. Min Act: -0.1700
Data Index: 1595962 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5541. Min Act: -0.1700
Data Index: 8108882 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5854. Min Act: -0.1700
Data Index: 4296514 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5541. Min Act: -0.1700
Data Index: 899607 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5541. Min Act: -0.1700
Data Index: 4250836 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5541. Min Act: -0.1700
Data Index: 5957881 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.4916. Min Act: -0.1700
Data Index: 1705957 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5229. Min Act: -0.1700
Data Index: 5866342 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.5229. Min Act: -0.1700
Data Index: 5837393 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.4916. Min Act: -0.1700
Data Index: 6478844 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.4604. Min Act: -0.1700
Data Index: 2581591 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.4291. Min Act: -0.1700
Data Index: 6942430 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.4291. Min Act: -0.1700
Data Index: 7948415 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0229. Min Range: -6.0229
Max Act: 5.4291. Min Act: -0.1700
Data Index: 127311 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19