Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2203 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.3900. Min Act: -0.1700
Data Index: 4831441 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.2025. Min Act: -0.1700
Data Index: 8430017 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1712. Min Act: -0.1700
Data Index: 2329257 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1400. Min Act: -0.1700
Data Index: 3370509 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1400. Min Act: -0.1700
Data Index: 7128719 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1087. Min Act: -0.1700
Data Index: 7075853 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1087. Min Act: -0.1700
Data Index: 524410 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.0150. Min Act: -0.1700
Data Index: 6072467 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.0462. Min Act: -0.1700
Data Index: 2490334 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9837. Min Act: -0.1700
Data Index: 648167 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9837. Min Act: -0.1700
Data Index: 8691546 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9525. Min Act: -0.1700
Data Index: 5611243 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9212. Min Act: -0.1700
Data Index: 217679 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 8320171 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9212. Min Act: -0.1700
Data Index: 2105552 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9212. Min Act: -0.1700
Data Index: 5878262 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9212. Min Act: -0.1700
Data Index: 6598542 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 4999625 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 7156523 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 5356535 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19