Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1264. Min Range: -6.1264
Max Act: 6.1264. Min Act: -0.1700
Data Index: 8106020 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1264. Min Range: -6.1264
Max Act: 6.0951. Min Act: -0.1700
Data Index: 320148 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1264. Min Range: -6.1264
Max Act: 6.0014. Min Act: -0.1700
Data Index: 4275891 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.9701. Min Act: -0.1700
Data Index: 5906752 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.9076. Min Act: -0.1700
Data Index: 6929882 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8764. Min Act: -0.1700
Data Index: 2395987 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8764. Min Act: -0.1700
Data Index: 7021047 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8764. Min Act: -0.1700
Data Index: 2864250 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8764. Min Act: -0.1700
Data Index: 5141422 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8764. Min Act: -0.1700
Data Index: 8498965 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8451. Min Act: -0.1700
Data Index: 345642 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8139. Min Act: -0.1700
Data Index: 6863941 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8139. Min Act: -0.1700
Data Index: 70249 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.7514. Min Act: -0.1700
Data Index: 4365682 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.7514. Min Act: -0.1700
Data Index: 6081285 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.7826. Min Act: -0.1700
Data Index: 2475131 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.7514. Min Act: -0.1700
Data Index: 5669528 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.7201. Min Act: -0.1700
Data Index: 737910 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.8139. Min Act: -0.1700
Data Index: 345640 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1264. Min Range: -6.1264
Max Act: 5.7201. Min Act: -0.1700
Data Index: 4983376 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19