Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.8821. Min Act: -0.1700
Data Index: 7803686 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.7257. Min Act: -0.1700
Data Index: 802054 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6945. Min Act: -0.1700
Data Index: 7803688 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6945. Min Act: -0.1700
Data Index: 2844451 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6632. Min Act: -0.1700
Data Index: 7803677 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6632. Min Act: -0.1700
Data Index: 7803671 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6319. Min Act: -0.1700
Data Index: 849113 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6319. Min Act: -0.1700
Data Index: 720964 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6006. Min Act: -0.1700
Data Index: 7803679 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6006. Min Act: -0.1700
Data Index: 7803673 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6006. Min Act: -0.1700
Data Index: 5166056 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6006. Min Act: -0.1700
Data Index: 294173 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.6006. Min Act: -0.1700
Data Index: 7803685 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5380. Min Act: -0.1700
Data Index: 8479887 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5693. Min Act: -0.1700
Data Index: 7803680 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5380. Min Act: -0.1700
Data Index: 2561638 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5693. Min Act: -0.1700
Data Index: 4991039 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5693. Min Act: -0.1700
Data Index: 7224884 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5380. Min Act: -0.1700
Data Index: 2561636 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8821. Min Range: -3.8821
Max Act: 3.5693. Min Act: -0.1700
Data Index: 3768524 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #19