Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4576 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.9099. Min Act: -0.1700
Data Index: 6624050 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.8474. Min Act: -0.1700
Data Index: 3869365 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.8786. Min Act: -0.1700
Data Index: 7025501 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 7684166 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.8161. Min Act: -0.1700
Data Index: 5817918 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 4861027 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 714072 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 5060890 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 985742 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7536. Min Act: -0.1700
Data Index: 5100192 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7849. Min Act: -0.1700
Data Index: 5248078 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7536. Min Act: -0.1700
Data Index: 5884949 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7536. Min Act: -0.1698
Data Index: 7077589 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7536. Min Act: -0.1700
Data Index: 4481528 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.6911. Min Act: -0.1700
Data Index: 1583646 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.6911. Min Act: -0.1700
Data Index: 6564888 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7224. Min Act: -0.1700
Data Index: 5780712 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7224. Min Act: -0.1700
Data Index: 455058 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7224. Min Act: -0.1700
Data Index: 5361584 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9099. Min Range: -5.9099
Max Act: 5.7224. Min Act: -0.1700
Data Index: 7249817 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19