Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.1930. Min Act: -0.1700
Data Index: 4279982 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.1430. Min Act: -0.1700
Data Index: 8534298 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0425. Min Act: -0.1700
Data Index: 5477837 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0425. Min Act: -0.1700
Data Index: 7286148 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0593. Min Act: -0.1700
Data Index: 8031877 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0088. Min Act: -0.1700
Data Index: 751609 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0425. Min Act: -0.1700
Data Index: 1886640 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0257. Min Act: -0.1700
Data Index: 5172601 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0088. Min Act: -0.1700
Data Index: 7873942 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0257. Min Act: -0.1700
Data Index: 7090917 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0088. Min Act: -0.1700
Data Index: 573464 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9919. Min Act: -0.1700
Data Index: 7949196 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9919. Min Act: -0.1700
Data Index: 4886325 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1930. Min Range: -2.1930
Max Act: 2.0088. Min Act: -0.1700
Data Index: 5893049 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9750. Min Act: -0.1700
Data Index: 5893747 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9919. Min Act: -0.1700
Data Index: 217195 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9750. Min Act: -0.1700
Data Index: 3245404 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9750. Min Act: -0.1700
Data Index: 2555371 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9580. Min Act: -0.1700
Data Index: 6558587 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1930. Min Range: -2.1930
Max Act: 1.9410. Min Act: -0.1700
Data Index: 6915466 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19