Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 962 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3369. Min Range: -4.3369
Max Act: 4.3369. Min Act: -0.1700
Data Index: 3839201 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3369. Min Range: -4.3369
Max Act: 4.2431. Min Act: -0.1700
Data Index: 6625072 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3369. Min Range: -4.3369
Max Act: 4.1494. Min Act: -0.1700
Data Index: 2096825 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3369. Min Range: -4.3369
Max Act: 4.0556. Min Act: -0.1700
Data Index: 5159995 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3369. Min Range: -4.3369
Max Act: 4.0243. Min Act: -0.1700
Data Index: 6845847 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.9618. Min Act: -0.1700
Data Index: 7738255 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.9618. Min Act: -0.1700
Data Index: 2374486 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.9618. Min Act: -0.1700
Data Index: 4790562 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8993. Min Act: -0.1700
Data Index: 2475287 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8993. Min Act: -0.1700
Data Index: 1050428 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8680. Min Act: -0.1700
Data Index: 63579 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8680. Min Act: -0.1700
Data Index: 6567481 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8680. Min Act: -0.1700
Data Index: 6552243 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8367. Min Act: -0.1700
Data Index: 1282716 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8680. Min Act: -0.1700
Data Index: 3663628 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8680. Min Act: -0.1700
Data Index: 6025481 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8680. Min Act: -0.1700
Data Index: 7312892 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8367. Min Act: -0.1700
Data Index: 4122715 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8367. Min Act: -0.1700
Data Index: 5563288 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3369. Min Range: -4.3369
Max Act: 3.8367. Min Act: -0.1700
Data Index: 7199128 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19