Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.6374. Min Act: -0.1700
Data Index: 4703972 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5749. Min Act: -0.1700
Data Index: 900256 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5749. Min Act: -0.1700
Data Index: 7682254 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 4082235 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 2666918 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 6644887 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5749. Min Act: -0.1700
Data Index: 2831543 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 6553615 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 882876 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 4702976 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 2712283 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.4812. Min Act: -0.1700
Data Index: 2081846 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 5042243 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 6824917 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5437. Min Act: -0.1700
Data Index: 7343521 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 483376 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 4389718 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 3730683 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 7744289 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6374. Min Range: -4.6374
Max Act: 4.5124. Min Act: -0.1700
Data Index: 8346028 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19