Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3840. Min Range: -6.3840
Max Act: 6.3840. Min Act: -0.1700
Data Index: 7775778 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.9777. Min Act: -0.1700
Data Index: 3522151 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3840. Min Range: -6.3840
Max Act: 6.0090. Min Act: -0.1700
Data Index: 2775833 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.9777. Min Act: -0.1700
Data Index: 2760457 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.9152. Min Act: -0.1700
Data Index: 7699906 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.9152. Min Act: -0.1700
Data Index: 7392223 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.8840. Min Act: -0.1700
Data Index: 3880606 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.7902. Min Act: -0.1700
Data Index: 1289013 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.7590. Min Act: -0.1700
Data Index: 2378859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.7590. Min Act: -0.1700
Data Index: 4272928 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6965. Min Act: -0.1700
Data Index: 7757863 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6965. Min Act: -0.1700
Data Index: 4035009 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6652. Min Act: -0.1700
Data Index: 6531173 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6965. Min Act: -0.1700
Data Index: 3421712 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6027. Min Act: -0.1700
Data Index: 8168479 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6340. Min Act: -0.1700
Data Index: 2714514 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6027. Min Act: -0.1700
Data Index: 3626229 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.5715. Min Act: -0.1700
Data Index: 2144028 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.6027. Min Act: -0.1700
Data Index: 5532416 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3840. Min Range: -6.3840
Max Act: 5.5402. Min Act: -0.1700
Data Index: 1839797 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19