Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4773 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0845. Min Range: -5.0845
Max Act: 5.0845. Min Act: -0.1700
Data Index: 335251 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0845. Min Range: -5.0845
Max Act: 5.0532. Min Act: -0.1700
Data Index: 2840627 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0845. Min Range: -5.0845
Max Act: 5.0220. Min Act: -0.1700
Data Index: 7878260 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0845. Min Range: -5.0845
Max Act: 5.0220. Min Act: -0.1700
Data Index: 6467688 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.9595. Min Act: -0.1700
Data Index: 5353495 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.9907. Min Act: -0.1700
Data Index: 7930172 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.9907. Min Act: -0.1700
Data Index: 4506859 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.9595. Min Act: -0.1700
Data Index: 2166164 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8657. Min Act: -0.1700
Data Index: 1798316 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8970. Min Act: -0.1700
Data Index: 6237961 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.9282. Min Act: -0.1700
Data Index: 7186421 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.9282. Min Act: -0.1700
Data Index: 27045 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8970. Min Act: -0.1700
Data Index: 7372010 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8345. Min Act: -0.1700
Data Index: 8682356 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8657. Min Act: -0.1700
Data Index: 4887046 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8657. Min Act: -0.1700
Data Index: 4145734 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8345. Min Act: -0.1700
Data Index: 3648873 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8345. Min Act: -0.1700
Data Index: 5742082 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8345. Min Act: -0.1700
Data Index: 6093342 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0845. Min Range: -5.0845
Max Act: 4.8345. Min Act: -0.1700
Data Index: 7651567 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19