Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.4621. Min Act: -0.1700
Data Index: 1130989 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.4308. Min Act: -0.1700
Data Index: 1230134 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.3683. Min Act: -0.1700
Data Index: 1130988 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.3371. Min Act: -0.1700
Data Index: 1619437 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.2433. Min Act: -0.1700
Data Index: 3712818 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.2121. Min Act: -0.1700
Data Index: 411509 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.1808. Min Act: -0.1700
Data Index: 244421 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.1808. Min Act: -0.1700
Data Index: 7814526 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.2121. Min Act: -0.1700
Data Index: 4776109 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.1496. Min Act: -0.1700
Data Index: 396075 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.1496. Min Act: -0.1700
Data Index: 4452610 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.1183. Min Act: -0.1700
Data Index: 4020342 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0871. Min Act: -0.1700
Data Index: 753149 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0871. Min Act: -0.1700
Data Index: 2682518 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0558. Min Act: -0.1700
Data Index: 8576941 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0558. Min Act: -0.1700
Data Index: 6819012 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0558. Min Act: -0.1700
Data Index: 2305011 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0246. Min Act: -0.1700
Data Index: 6013030 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0558. Min Act: -0.1700
Data Index: 3231147 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4621. Min Range: -5.4621
Max Act: 5.0246. Min Act: -0.1700
Data Index: 2218204 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19