Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.3438. Min Act: -0.1700
Data Index: 2516211 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.2810. Min Act: -0.1700
Data Index: 7486447 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.2181. Min Act: -0.1700
Data Index: 394942 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.2024. Min Act: -0.1700
Data Index: 7317917 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.1395. Min Act: -0.1700
Data Index: 3277767 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0607. Min Act: -0.1700
Data Index: 2702646 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0607. Min Act: -0.1700
Data Index: 844091 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0449. Min Act: -0.1700
Data Index: 6976299 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0291. Min Act: -0.1700
Data Index: 8211966 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0291. Min Act: -0.1700
Data Index: 1652950 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3438. Min Range: -3.3438
Max Act: 3.0133. Min Act: -0.1700
Data Index: 3037163 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 6725560 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 2311481 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9817. Min Act: -0.1700
Data Index: 7308752 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9659. Min Act: -0.1700
Data Index: 1221885 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9659. Min Act: -0.1700
Data Index: 1943632 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9500. Min Act: -0.1700
Data Index: 896430 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9500. Min Act: -0.1700
Data Index: 1559203 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9184. Min Act: -0.1700
Data Index: 2848697 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3438. Min Range: -3.3438
Max Act: 2.9184. Min Act: -0.1700
Data Index: 4824543 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19