Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 632 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0938. Min Range: -7.0938
Max Act: 7.0938. Min Act: -0.1700
Data Index: 3411617 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.9688. Min Act: -0.1700
Data Index: 4757900 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.9063. Min Act: -0.1700
Data Index: 4042173 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.9063. Min Act: -0.1700
Data Index: 1739592 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.8750. Min Act: -0.1700
Data Index: 6946533 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.8438. Min Act: -0.1700
Data Index: 4143009 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.7500. Min Act: -0.1700
Data Index: 2529401 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.7188. Min Act: -0.1700
Data Index: 5518746 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.8125. Min Act: -0.1700
Data Index: 8406846 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.6875. Min Act: -0.1700
Data Index: 6897959 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.6875. Min Act: -0.1700
Data Index: 1595765 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.6563. Min Act: -0.1700
Data Index: 1768644 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.6563. Min Act: -0.1700
Data Index: 4578888 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.5938. Min Act: -0.1700
Data Index: 2099849 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.5938. Min Act: -0.1700
Data Index: 5757300 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.5938. Min Act: -0.1700
Data Index: 5607376 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.5625. Min Act: -0.1700
Data Index: 2648681 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.5625. Min Act: -0.1700
Data Index: 2635890 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.5313. Min Act: -0.1700
Data Index: 5511449 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0938. Min Range: -7.0938
Max Act: 6.4688. Min Act: -0.1700
Data Index: 3085694 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19