Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 147 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0858. Min Range: -5.0858
Max Act: 5.0858. Min Act: -0.1700
Data Index: 3020040 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.4295. Min Act: -0.1700
Data Index: 8059964 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.4608. Min Act: -0.1700
Data Index: 1399877 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3983. Min Act: -0.1700
Data Index: 6779406 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3983. Min Act: -0.1700
Data Index: 3963063 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3670. Min Act: -0.1700
Data Index: 2615687 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3670. Min Act: -0.1700
Data Index: 7214851 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3670. Min Act: -0.1700
Data Index: 638433 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3358. Min Act: -0.1700
Data Index: 7792041 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3045. Min Act: -0.1700
Data Index: 119258 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.3358. Min Act: -0.1700
Data Index: 2136585 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2733. Min Act: -0.1700
Data Index: 3760516 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2733. Min Act: -0.1700
Data Index: 5164203 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2733. Min Act: -0.1700
Data Index: 7879793 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2733. Min Act: -0.1700
Data Index: 6506988 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2420. Min Act: -0.1700
Data Index: 8328895 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2733. Min Act: -0.1700
Data Index: 1179459 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2420. Min Act: -0.1700
Data Index: 4353675 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2420. Min Act: -0.1700
Data Index: 1702764 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0858. Min Range: -5.0858
Max Act: 4.2420. Min Act: -0.1700
Data Index: 3256163 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19