Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.2106. Min Act: -0.1700
Data Index: 4221887 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.1319. Min Act: -0.1700
Data Index: 522122 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.1319. Min Act: -0.1700
Data Index: 6321516 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0847. Min Act: -0.1700
Data Index: 2166388 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.1004. Min Act: -0.1700
Data Index: 4735519 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.1004. Min Act: -0.1700
Data Index: 8004340 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0689. Min Act: -0.1700
Data Index: 8140355 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0058. Min Act: -0.1700
Data Index: 3231196 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0058. Min Act: -0.1700
Data Index: 6924908 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0373. Min Act: -0.1700
Data Index: 4090227 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0216. Min Act: -0.1700
Data Index: 2152950 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0058. Min Act: -0.1700
Data Index: 895689 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0216. Min Act: -0.1700
Data Index: 4136398 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2106. Min Range: -3.2106
Max Act: 3.0058. Min Act: -0.1700
Data Index: 7515559 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2106. Min Range: -3.2106
Max Act: 2.9741. Min Act: -0.1700
Data Index: 2514090 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2106. Min Range: -3.2106
Max Act: 2.9741. Min Act: -0.1700
Data Index: 841470 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2106. Min Range: -3.2106
Max Act: 2.9899. Min Act: -0.1700
Data Index: 3730134 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2106. Min Range: -3.2106
Max Act: 2.9899. Min Act: -0.1700
Data Index: 7134821 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2106. Min Range: -3.2106
Max Act: 2.9266. Min Act: -0.1700
Data Index: 7915655 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2106. Min Range: -3.2106
Max Act: 2.9425. Min Act: -0.1700
Data Index: 3900686 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19