Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3027 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.7859. Min Act: -0.1700
Data Index: 7418124 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.6609. Min Act: -0.1700
Data Index: 5592823 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.6296. Min Act: -0.1700
Data Index: 5255329 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.5359. Min Act: -0.1700
Data Index: 8077104 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.5046. Min Act: -0.1700
Data Index: 4414518 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.5046. Min Act: -0.1700
Data Index: 3524448 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.4734. Min Act: -0.1700
Data Index: 5746137 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.4734. Min Act: -0.1700
Data Index: 3697781 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.4734. Min Act: -0.1700
Data Index: 5208678 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.4109. Min Act: -0.1700
Data Index: 189717 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3796. Min Act: -0.1700
Data Index: 7692841 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3796. Min Act: -0.1700
Data Index: 5746860 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3796. Min Act: -0.1700
Data Index: 5565948 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 5741210 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 5700502 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 5220115 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 5231178 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 2103521 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 7337252 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7859. Min Range: -5.7859
Max Act: 5.3484. Min Act: -0.1700
Data Index: 6129475 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19