Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5000 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0781. Min Range: -5.0781
Max Act: 5.0781. Min Act: -0.1700
Data Index: 7200343 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0781. Min Range: -5.0781
Max Act: 5.0781. Min Act: -0.1700
Data Index: 8816270 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0781. Min Range: -5.0781
Max Act: 5.0468. Min Act: -0.1700
Data Index: 2797817 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0781. Min Range: -5.0781
Max Act: 5.0156. Min Act: -0.1700
Data Index: 5383740 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0781. Min Range: -5.0781
Max Act: 5.0156. Min Act: -0.1700
Data Index: 7259998 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.9843. Min Act: -0.1700
Data Index: 4303118 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.9218. Min Act: -0.1700
Data Index: 7200341 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.9218. Min Act: -0.1700
Data Index: 2323846 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.9218. Min Act: -0.1700
Data Index: 3760840 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.9218. Min Act: -0.1700
Data Index: 6705024 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.8906. Min Act: -0.1700
Data Index: 433868 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.8593. Min Act: -0.1700
Data Index: 4340178 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.8593. Min Act: -0.1700
Data Index: 7259999 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.8593. Min Act: -0.1700
Data Index: 447026 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.8593. Min Act: -0.1700
Data Index: 3216448 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.8281. Min Act: -0.1700
Data Index: 2759044 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.7968. Min Act: -0.1700
Data Index: 6346496 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.7968. Min Act: -0.1700
Data Index: 886612 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.7968. Min Act: -0.1700
Data Index: 7842596 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0781. Min Range: -5.0781
Max Act: 4.7656. Min Act: -0.1700
Data Index: 5665254 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19