Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.4472. Min Act: -0.1700
Data Index: 5131391 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.3847. Min Act: -0.1700
Data Index: 3659409 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.2909. Min Act: -0.1700
Data Index: 4282555 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.2909. Min Act: -0.1700
Data Index: 1845653 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.3222. Min Act: -0.1700
Data Index: 5918122 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.2909. Min Act: -0.1700
Data Index: 2779591 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.2284. Min Act: -0.1700
Data Index: 6746974 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.2284. Min Act: -0.1700
Data Index: 6289844 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1972. Min Act: -0.1700
Data Index: 3838016 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.2284. Min Act: -0.1700
Data Index: 7463598 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1972. Min Act: -0.1700
Data Index: 276675 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1659. Min Act: -0.1700
Data Index: 3965111 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1972. Min Act: -0.1700
Data Index: 2053054 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1347. Min Act: -0.1700
Data Index: 7960886 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1034. Min Act: -0.1700
Data Index: 5533068 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1347. Min Act: -0.1700
Data Index: 2764987 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1034. Min Act: -0.1700
Data Index: 4487332 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1659. Min Act: -0.1700
Data Index: 1676277 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.1034. Min Act: -0.1700
Data Index: 4298315 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4472. Min Range: -5.4472
Max Act: 5.0722. Min Act: -0.1700
Data Index: 3824911 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19