Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0689. Min Range: -3.0689
Max Act: 3.0689. Min Act: -0.1700
Data Index: 736847 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0689. Min Range: -3.0689
Max Act: 3.0215. Min Act: -0.1700
Data Index: 6531138 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0689. Min Range: -3.0689
Max Act: 3.0215. Min Act: -0.1700
Data Index: 3034523 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.9583. Min Act: -0.1700
Data Index: 3108579 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.9583. Min Act: -0.1700
Data Index: 3108589 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8791. Min Act: -0.1700
Data Index: 4373072 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.9108. Min Act: -0.1700
Data Index: 4611110 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8791. Min Act: -0.1700
Data Index: 3865458 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8791. Min Act: -0.1700
Data Index: 20829 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8791. Min Act: -0.1700
Data Index: 3945559 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8791. Min Act: -0.1700
Data Index: 1146553 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8632. Min Act: -0.1700
Data Index: 6506390 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8632. Min Act: -0.1700
Data Index: 3863368 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8632. Min Act: -0.1700
Data Index: 7016376 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8791. Min Act: -0.1700
Data Index: 2707517 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8473. Min Act: -0.1700
Data Index: 3522356 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8473. Min Act: -0.1700
Data Index: 3415859 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8155. Min Act: -0.1700
Data Index: 6150897 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8314. Min Act: -0.1700
Data Index: 2614219 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0689. Min Range: -3.0689
Max Act: 2.8314. Min Act: -0.1700
Data Index: 3522366 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19