Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.6884. Min Act: -0.1700
Data Index: 5038509 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.6258. Min Act: -0.1700
Data Index: 7600219 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.5945. Min Act: -0.1700
Data Index: 7123175 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.5788. Min Act: -0.1700
Data Index: 7838738 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.5632. Min Act: -0.1700
Data Index: 8278387 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.5632. Min Act: -0.1700
Data Index: 1965534 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4849. Min Act: -0.1700
Data Index: 8528993 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4692. Min Act: -0.1700
Data Index: 2446276 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4692. Min Act: -0.1700
Data Index: 8137646 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4535. Min Act: -0.1700
Data Index: 1572958 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4692. Min Act: -0.1700
Data Index: 1920568 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4379. Min Act: -0.1700
Data Index: 1423624 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4535. Min Act: -0.1700
Data Index: 7173968 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4379. Min Act: -0.1700
Data Index: 8785971 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4379. Min Act: -0.1700
Data Index: 3697057 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4379. Min Act: -0.1700
Data Index: 8173166 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4379. Min Act: -0.1700
Data Index: 6602457 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4222. Min Act: -0.1700
Data Index: 6331534 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4379. Min Act: -0.1700
Data Index: 4483643 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6884. Min Range: -3.6884
Max Act: 3.4222. Min Act: -0.1700
Data Index: 5817771 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19