Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.2564. Min Act: -0.1700
Data Index: 305717 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.2249. Min Act: -0.1700
Data Index: 5235843 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1935. Min Act: -0.1700
Data Index: 2945009 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1935. Min Act: -0.1700
Data Index: 4111014 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1935. Min Act: -0.1700
Data Index: 3442150 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1620. Min Act: -0.1700
Data Index: 6252457 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1305. Min Act: -0.1700
Data Index: 4672822 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1148. Min Act: -0.1700
Data Index: 6594369 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.1148. Min Act: -0.1700
Data Index: 2516459 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 6161047 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 4502877 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 4672812 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0990. Min Act: -0.1700
Data Index: 1183183 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0517. Min Act: -0.1700
Data Index: 774290 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 663421 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0517. Min Act: -0.1700
Data Index: 8598286 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 789079 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 8798248 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0675. Min Act: -0.1700
Data Index: 5602162 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2564. Min Range: -3.2564
Max Act: 3.0359. Min Act: -0.1700
Data Index: 2839695 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19