Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 927 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1519. Min Range: -4.1519
Max Act: 4.1519. Min Act: -0.1700
Data Index: 3962778 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1519. Min Range: -4.1519
Max Act: 4.0894. Min Act: -0.1700
Data Index: 4638734 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1519. Min Range: -4.1519
Max Act: 4.0269. Min Act: -0.1700
Data Index: 4842153 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9956. Min Act: -0.1700
Data Index: 3434466 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9331. Min Act: -0.1700
Data Index: 1975216 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9331. Min Act: -0.1700
Data Index: 3505287 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9331. Min Act: -0.1700
Data Index: 4443863 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9331. Min Act: -0.1700
Data Index: 7036701 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9331. Min Act: -0.1700
Data Index: 8431448 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9018. Min Act: -0.1700
Data Index: 5899553 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.9018. Min Act: -0.1700
Data Index: 6762797 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8393. Min Act: -0.1700
Data Index: 6540891 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8705. Min Act: -0.1700
Data Index: 8526056 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8080. Min Act: -0.1700
Data Index: 1803275 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8705. Min Act: -0.1700
Data Index: 3006574 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8393. Min Act: -0.1700
Data Index: 3625786 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8393. Min Act: -0.1700
Data Index: 2355328 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8393. Min Act: -0.1700
Data Index: 3278181 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8393. Min Act: -0.1700
Data Index: 2549450 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1519. Min Range: -4.1519
Max Act: 3.8080. Min Act: -0.1700
Data Index: 1205798 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19