Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0196. Min Range: -5.0196
Max Act: 5.0196. Min Act: -0.1700
Data Index: 6372121 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9884. Min Act: -0.1700
Data Index: 1193007 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9571. Min Act: -0.1700
Data Index: 6311835 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8946. Min Act: -0.1700
Data Index: 1852197 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9259. Min Act: -0.1700
Data Index: 7734739 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9259. Min Act: -0.1700
Data Index: 964186 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9259. Min Act: -0.1700
Data Index: 1621389 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9259. Min Act: -0.1700
Data Index: 3184279 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8634. Min Act: -0.1700
Data Index: 604168 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8634. Min Act: -0.1700
Data Index: 2866828 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.9259. Min Act: -0.1700
Data Index: 3813089 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8946. Min Act: -0.1700
Data Index: 2506461 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8946. Min Act: -0.1700
Data Index: 6859926 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8634. Min Act: -0.1700
Data Index: 4011295 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8634. Min Act: -0.1700
Data Index: 2100387 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8634. Min Act: -0.1700
Data Index: 8323859 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8321. Min Act: -0.1700
Data Index: 7156423 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8321. Min Act: -0.1700
Data Index: 5391308 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8321. Min Act: -0.1700
Data Index: 6434029 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0196. Min Range: -5.0196
Max Act: 4.8321. Min Act: -0.1700
Data Index: 7508478 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19