Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2260. Min Range: -6.2260
Max Act: 6.1948. Min Act: -0.1700
Data Index: 7589239 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2260. Min Range: -6.2260
Max Act: 6.1948. Min Act: -0.1700
Data Index: 5894569 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2260. Min Range: -6.2260
Max Act: 6.2260. Min Act: -0.1700
Data Index: 949299 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2260. Min Range: -6.2260
Max Act: 6.0385. Min Act: -0.1700
Data Index: 893383 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2260. Min Range: -6.2260
Max Act: 6.0073. Min Act: -0.1700
Data Index: 6158861 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2260. Min Range: -6.2260
Max Act: 6.0073. Min Act: -0.1700
Data Index: 3605490 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9760. Min Act: -0.1700
Data Index: 153116 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9448. Min Act: -0.1700
Data Index: 4493355 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9135. Min Act: -0.1700
Data Index: 2408966 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9135. Min Act: -0.1700
Data Index: 5450524 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9135. Min Act: -0.1700
Data Index: 295028 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9135. Min Act: -0.1700
Data Index: 4113386 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.9135. Min Act: -0.1700
Data Index: 3579627 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8823. Min Act: -0.1700
Data Index: 352017 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8823. Min Act: -0.1700
Data Index: 2104587 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8823. Min Act: -0.1700
Data Index: 7217177 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8510. Min Act: -0.1700
Data Index: 697346 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8510. Min Act: -0.1700
Data Index: 6073507 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8823. Min Act: -0.1700
Data Index: 5637549 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2260. Min Range: -6.2260
Max Act: 5.8510. Min Act: -0.1700
Data Index: 7377987 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19