Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3719 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3899. Min Range: -5.3899
Max Act: 5.3899. Min Act: -0.1700
Data Index: 3016801 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3899. Min Range: -5.3899
Max Act: 5.2336. Min Act: -0.1700
Data Index: 8585471 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3899. Min Range: -5.3899
Max Act: 5.1086. Min Act: -0.1700
Data Index: 8170167 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3899. Min Range: -5.3899
Max Act: 5.0461. Min Act: -0.1700
Data Index: 5278667 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3899. Min Range: -5.3899
Max Act: 5.0461. Min Act: -0.1700
Data Index: 5130440 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3899. Min Range: -5.3899
Max Act: 5.0461. Min Act: -0.1700
Data Index: 2874149 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9524. Min Act: -0.1700
Data Index: 1524012 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9211. Min Act: -0.1700
Data Index: 2442924 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9524. Min Act: -0.1700
Data Index: 343734 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9211. Min Act: -0.1700
Data Index: 7617977 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9211. Min Act: -0.1700
Data Index: 2569350 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9211. Min Act: -0.1700
Data Index: 2912269 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.8899. Min Act: -0.1700
Data Index: 1747722 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.8586. Min Act: -0.1700
Data Index: 6873577 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.9211. Min Act: -0.1700
Data Index: 8407415 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.8586. Min Act: -0.1700
Data Index: 4082634 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.8274. Min Act: -0.1700
Data Index: 8317564 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.8899. Min Act: -0.1700
Data Index: 5411437 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.7961. Min Act: -0.1700
Data Index: 4840049 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3899. Min Range: -5.3899
Max Act: 4.7961. Min Act: -0.1700
Data Index: 3270902 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19