Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 747 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6130. Min Range: -8.6130
Max Act: 8.6130. Min Act: -0.1700
Data Index: 44790 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6130. Min Range: -8.6130
Max Act: 8.3630. Min Act: -0.1700
Data Index: 2290294 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6130. Min Range: -8.6130
Max Act: 8.0817. Min Act: -0.1700
Data Index: 594341 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6130. Min Range: -8.6130
Max Act: 8.1130. Min Act: -0.1700
Data Index: 3001981 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6130. Min Range: -8.6130
Max Act: 8.1130. Min Act: -0.1700
Data Index: 6214523 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8942. Min Act: -0.1700
Data Index: 247291 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.9567. Min Act: -0.1700
Data Index: 58717 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8942. Min Act: -0.1700
Data Index: 3699838 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8630. Min Act: -0.1700
Data Index: 8664799 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8005. Min Act: -0.1700
Data Index: 4606794 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8942. Min Act: -0.1700
Data Index: 7575672 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8005. Min Act: -0.1700
Data Index: 7785541 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.8317. Min Act: -0.1700
Data Index: 7311186 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7380. Min Act: -0.1700
Data Index: 2855917 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7692. Min Act: -0.1700
Data Index: 5104047 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7067. Min Act: -0.1700
Data Index: 469117 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7692. Min Act: -0.1700
Data Index: 314746 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7067. Min Act: -0.1700
Data Index: 8332152 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7067. Min Act: -0.1700
Data Index: 5161127 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6130. Min Range: -8.6130
Max Act: 7.7067. Min Act: -0.1700
Data Index: 1311237 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19