Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3784 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.5365. Min Act: -0.1700
Data Index: 4933100 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3490. Min Act: -0.1700
Data Index: 4933102 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3178. Min Act: -0.1700
Data Index: 8793983 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.3178. Min Act: -0.1700
Data Index: 3718143 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.2865. Min Act: -0.1700
Data Index: 6713991 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.2553. Min Act: -0.1700
Data Index: 4933101 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.1928. Min Act: -0.1700
Data Index: 728501 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.1615. Min Act: -0.1700
Data Index: 3718142 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0990. Min Act: -0.1700
Data Index: 728500 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0990. Min Act: -0.1700
Data Index: 4533120 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0990. Min Act: -0.1700
Data Index: 1672673 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0678. Min Act: -0.1700
Data Index: 6331085 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0678. Min Act: -0.1700
Data Index: 7234770 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0365. Min Act: -0.1700
Data Index: 5092917 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0053. Min Act: -0.1700
Data Index: 852277 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5365. Min Range: -5.5365
Max Act: 5.0365. Min Act: -0.1700
Data Index: 3051827 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5365. Min Range: -5.5365
Max Act: 4.9740. Min Act: -0.1700
Data Index: 2767128 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5365. Min Range: -5.5365
Max Act: 4.9740. Min Act: -0.1700
Data Index: 8574901 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5365. Min Range: -5.5365
Max Act: 4.9740. Min Act: -0.1700
Data Index: 7479139 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5365. Min Range: -5.5365
Max Act: 4.9740. Min Act: -0.1700
Data Index: 3455466 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19