Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 566 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1150. Min Range: -5.1150
Max Act: 5.1150. Min Act: -0.1700
Data Index: 1189259 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1150. Min Range: -5.1150
Max Act: 5.0213. Min Act: -0.1700
Data Index: 3554583 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1150. Min Range: -5.1150
Max Act: 5.0525. Min Act: -0.1700
Data Index: 1374983 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.9900. Min Act: -0.1700
Data Index: 101222 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1150. Min Range: -5.1150
Max Act: 5.0213. Min Act: -0.1700
Data Index: 5287354 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.9588. Min Act: -0.1700
Data Index: 7864829 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.9275. Min Act: -0.1700
Data Index: 958528 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8963. Min Act: -0.1700
Data Index: 5060482 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.9275. Min Act: -0.1700
Data Index: 4069051 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.9275. Min Act: -0.1700
Data Index: 4708521 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8650. Min Act: -0.1700
Data Index: 2572089 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8650. Min Act: -0.1700
Data Index: 1933499 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8963. Min Act: -0.1700
Data Index: 3036954 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8963. Min Act: -0.1700
Data Index: 2187488 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8650. Min Act: -0.1700
Data Index: 3355880 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8338. Min Act: -0.1700
Data Index: 225288 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8338. Min Act: -0.1700
Data Index: 6115084 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8963. Min Act: -0.1700
Data Index: 2206738 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8650. Min Act: -0.1700
Data Index: 4585898 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1150. Min Range: -5.1150
Max Act: 4.8650. Min Act: -0.1700
Data Index: 991569 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19