Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2082 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.9592. Min Act: -0.1700
Data Index: 5795127 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.9434. Min Act: -0.1700
Data Index: 6482841 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.9276. Min Act: -0.1700
Data Index: 2179150 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8800. Min Act: -0.1700
Data Index: 5914539 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8324. Min Act: -0.1700
Data Index: 1442922 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8324. Min Act: -0.1700
Data Index: 335968 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8482. Min Act: -0.1700
Data Index: 3878908 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8164. Min Act: -0.1700
Data Index: 2671652 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8005. Min Act: -0.1700
Data Index: 823620 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8164. Min Act: -0.1700
Data Index: 6744250 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7846. Min Act: -0.1700
Data Index: 8224311 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.8164. Min Act: -0.1700
Data Index: 2333191 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7687. Min Act: -0.1700
Data Index: 7271688 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7846. Min Act: -0.1700
Data Index: 3616918 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7527. Min Act: -0.1700
Data Index: 5905205 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7527. Min Act: -0.1700
Data Index: 6210292 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7527. Min Act: -0.1700
Data Index: 1860734 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7687. Min Act: -0.1700
Data Index: 2493748 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7527. Min Act: -0.1700
Data Index: 1860201 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9592. Min Range: -2.9592
Max Act: 2.7367. Min Act: -0.1700
Data Index: 1160640 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19