Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 474 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.5375. Min Act: -0.1700
Data Index: 893403 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.5218. Min Act: -0.1700
Data Index: 255071 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.5062. Min Act: -0.1700
Data Index: 8820840 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4435. Min Act: -0.1700
Data Index: 3985286 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4592. Min Act: -0.1700
Data Index: 8690961 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4748. Min Act: -0.1700
Data Index: 2872028 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4592. Min Act: -0.1700
Data Index: 4920954 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4278. Min Act: -0.1700
Data Index: 8089830 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4592. Min Act: -0.1700
Data Index: 3755690 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4592. Min Act: -0.1700
Data Index: 1879238 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4435. Min Act: -0.1700
Data Index: 4871573 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4592. Min Act: -0.1700
Data Index: 2372600 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4278. Min Act: -0.1700
Data Index: 1358132 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4278. Min Act: -0.1700
Data Index: 3702937 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4435. Min Act: -0.1700
Data Index: 5025606 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.3965. Min Act: -0.1700
Data Index: 2692719 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.3651. Min Act: -0.1700
Data Index: 6754059 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4278. Min Act: -0.1700
Data Index: 2912821 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.4278. Min Act: -0.1700
Data Index: 4244240 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5375. Min Range: -3.5375
Max Act: 3.3965. Min Act: -0.1700
Data Index: 809057 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19