Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2012 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0658. Min Range: -5.0658
Max Act: 5.0658. Min Act: -0.1700
Data Index: 5854818 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0658. Min Range: -5.0658
Max Act: 5.0346. Min Act: -0.1700
Data Index: 6569710 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0658. Min Range: -5.0658
Max Act: 5.0033. Min Act: -0.1700
Data Index: 4983319 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9408. Min Act: -0.1700
Data Index: 4471188 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9408. Min Act: -0.1700
Data Index: 5467712 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9408. Min Act: -0.1700
Data Index: 8446924 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9408. Min Act: -0.1700
Data Index: 4175663 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 4270307 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.8783. Min Act: -0.1700
Data Index: 4178142 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 6106454 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 5441238 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 1492098 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 5928792 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 6594096 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.8783. Min Act: -0.1700
Data Index: 3707140 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.8783. Min Act: -0.1700
Data Index: 6073307 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.9096. Min Act: -0.1700
Data Index: 4831505 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.8783. Min Act: -0.1700
Data Index: 1073865 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.8783. Min Act: -0.1700
Data Index: 792998 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0658. Min Range: -5.0658
Max Act: 4.8783. Min Act: -0.1700
Data Index: 544919 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19