Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9612. Min Act: -0.1700
Data Index: 6016964 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9781. Min Act: -0.1700
Data Index: 4368706 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9612. Min Act: -0.1700
Data Index: 5676593 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9612. Min Act: -0.1700
Data Index: 1362943 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9612. Min Act: -0.1700
Data Index: 7886049 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9612. Min Act: -0.1700
Data Index: 6683850 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9612. Min Act: -0.1700
Data Index: 4111149 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9442. Min Act: -0.1700
Data Index: 4066238 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9442. Min Act: -0.1700
Data Index: 4915712 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9442. Min Act: -0.1700
Data Index: 5820344 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9272. Min Act: -0.1700
Data Index: 5722122 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9272. Min Act: -0.1700
Data Index: 2174008 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9272. Min Act: -0.1700
Data Index: 1086549 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9102. Min Act: -0.1700
Data Index: 1819961 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9272. Min Act: -0.1700
Data Index: 2827598 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9272. Min Act: -0.1700
Data Index: 7257096 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9272. Min Act: -0.1700
Data Index: 7500076 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9102. Min Act: -0.1698
Data Index: 4569338 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9102. Min Act: -0.1700
Data Index: 7211181 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9781. Min Range: -1.9781
Max Act: 1.9102. Min Act: -0.1700
Data Index: 5103966 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19