Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.8648. Min Act: -0.1700
Data Index: 259340 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.2398. Min Act: -0.1700
Data Index: 4381160 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.2085. Min Act: -0.1700
Data Index: 8273313 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.1773. Min Act: -0.1700
Data Index: 7763717 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.1148. Min Act: -0.1700
Data Index: 2641808 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 7158511 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8648. Min Range: -6.8648
Max Act: 6.0523. Min Act: -0.1700
Data Index: 2018108 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.9898. Min Act: -0.1700
Data Index: 2836583 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.9898. Min Act: -0.1700
Data Index: 6572073 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.9898. Min Act: -0.1700
Data Index: 4239010 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.9898. Min Act: -0.1700
Data Index: 5143964 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.9585. Min Act: -0.1700
Data Index: 1270104 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.9273. Min Act: -0.1700
Data Index: 2019686 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8648. Min Act: -0.1700
Data Index: 82113 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8960. Min Act: -0.1700
Data Index: 601216 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8960. Min Act: -0.1700
Data Index: 361959 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8648. Min Act: -0.1700
Data Index: 8183406 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6977911 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6076536 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8648. Min Range: -6.8648
Max Act: 5.8648. Min Act: -0.1700
Data Index: 5998427 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19