Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0258. Min Range: -7.0258
Max Act: 7.0258. Min Act: -0.1700
Data Index: 186127 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.8071. Min Act: -0.1700
Data Index: 8302619 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.6508. Min Act: -0.1700
Data Index: 7201131 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.6196. Min Act: -0.1700
Data Index: 7973926 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.6196. Min Act: -0.1700
Data Index: 6329217 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.6196. Min Act: -0.1700
Data Index: 1928366 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.5258. Min Act: -0.1700
Data Index: 8065004 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.5258. Min Act: -0.1700
Data Index: 1504596 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.5258. Min Act: -0.1700
Data Index: 2220065 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4946. Min Act: -0.1700
Data Index: 4748853 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4946. Min Act: -0.1700
Data Index: 8181252 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4946. Min Act: -0.1700
Data Index: 4230451 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4633. Min Act: -0.1700
Data Index: 733321 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4633. Min Act: -0.1700
Data Index: 426057 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4633. Min Act: -0.1700
Data Index: 3461511 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4321. Min Act: -0.1700
Data Index: 1169566 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.4633. Min Act: -0.1700
Data Index: 1858271 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.3696. Min Act: -0.1700
Data Index: 1190721 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.3383. Min Act: -0.1700
Data Index: 1187181 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0258. Min Range: -7.0258
Max Act: 6.3383. Min Act: -0.1700
Data Index: 4772020 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19