Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0074. Min Range: -7.0074
Max Act: 7.0074. Min Act: -0.1700
Data Index: 559430 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.9761. Min Act: -0.1700
Data Index: 7826617 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.9136. Min Act: -0.1700
Data Index: 5607538 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.9449. Min Act: -0.1700
Data Index: 6485938 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.7886. Min Act: -0.1700
Data Index: 8816020 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.7261. Min Act: -0.1700
Data Index: 8470762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.7261. Min Act: -0.1700
Data Index: 8376288 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6636. Min Act: -0.1700
Data Index: 1762003 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6324. Min Act: -0.1700
Data Index: 1843178 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6636. Min Act: -0.1700
Data Index: 1207260 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6636. Min Act: -0.1700
Data Index: 2215929 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6011. Min Act: -0.1700
Data Index: 622121 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6324. Min Act: -0.1700
Data Index: 1041022 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6011. Min Act: -0.1700
Data Index: 8755797 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6011. Min Act: -0.1700
Data Index: 6953149 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.5699. Min Act: -0.1700
Data Index: 4078755 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.6011. Min Act: -0.1700
Data Index: 815577 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.5699. Min Act: -0.1700
Data Index: 6388242 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3695270 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0074. Min Range: -7.0074
Max Act: 6.5386. Min Act: -0.1700
Data Index: 1438899 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19