Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.5077. Min Act: -0.1700
Data Index: 7331850 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.4139. Min Act: -0.1700
Data Index: 8059406 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.3827. Min Act: -0.1700
Data Index: 1507876 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.3514. Min Act: -0.1700
Data Index: 4400254 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.2577. Min Act: -0.1700
Data Index: 1507875 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.2264. Min Act: -0.1700
Data Index: 587779 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.2577. Min Act: -0.1700
Data Index: 5722383 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.2264. Min Act: -0.1700
Data Index: 4400617 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1952. Min Act: -0.1700
Data Index: 7801262 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1952. Min Act: -0.1700
Data Index: 7351767 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1952. Min Act: -0.1700
Data Index: 4867512 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1639. Min Act: -0.1700
Data Index: 4867516 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1639. Min Act: -0.1700
Data Index: 1374225 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1639. Min Act: -0.1700
Data Index: 7662987 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1639. Min Act: -0.1700
Data Index: 7801255 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1639. Min Act: -0.1700
Data Index: 6423648 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1327. Min Act: -0.1700
Data Index: 4596839 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.1327. Min Act: -0.1700
Data Index: 7927884 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.0702. Min Act: -0.1700
Data Index: 2847935 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5077. Min Range: -5.5077
Max Act: 5.0702. Min Act: -0.1700
Data Index: 206074 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19