Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.5960. Min Act: -0.1700
Data Index: 1117751 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.2523. Min Act: -0.1700
Data Index: 7175482 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.3148. Min Act: -0.1700
Data Index: 6595725 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.1898. Min Act: -0.1700
Data Index: 7175481 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.2210. Min Act: -0.1700
Data Index: 908825 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.2835. Min Act: -0.1700
Data Index: 6097833 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.1898. Min Act: -0.1700
Data Index: 1663678 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.1585. Min Act: -0.1700
Data Index: 68046 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.1585. Min Act: -0.1700
Data Index: 1875929 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.1273. Min Act: -0.1700
Data Index: 7372852 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0960. Min Act: -0.1700
Data Index: 1048196 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.1273. Min Act: -0.1700
Data Index: 740898 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 1000214 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 1629628 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 6456948 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5671246 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 2601359 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0335. Min Act: -0.1700
Data Index: 2703027 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5960. Min Range: -5.5960
Max Act: 5.0023. Min Act: -0.1700
Data Index: 2734024 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5960. Min Range: -5.5960
Max Act: 4.9710. Min Act: -0.1700
Data Index: 5632295 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19