Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5416 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0937. Min Range: -8.0937
Max Act: 8.0937. Min Act: -0.1700
Data Index: 2957583 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0937. Min Range: -8.0937
Max Act: 8.0312. Min Act: -0.1700
Data Index: 8371139 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 5235572 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 6471733 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.9062. Min Act: -0.1700
Data Index: 4371621 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.8437. Min Act: -0.1700
Data Index: 5828040 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 2300366 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.7812. Min Act: -0.1700
Data Index: 749467 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.6562. Min Act: -0.1700
Data Index: 4943948 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.6562. Min Act: -0.1700
Data Index: 8015935 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.5624. Min Act: -0.1700
Data Index: 5051004 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.5312. Min Act: -0.1700
Data Index: 5894754 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.5312. Min Act: -0.1700
Data Index: 7873622 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4999. Min Act: -0.1700
Data Index: 4804199 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4999. Min Act: -0.1700
Data Index: 7935064 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4687. Min Act: -0.1700
Data Index: 6586510 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4687. Min Act: -0.1700
Data Index: 6999130 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4687. Min Act: -0.1700
Data Index: 6474077 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4374. Min Act: -0.1700
Data Index: 1879551 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0937. Min Range: -8.0937
Max Act: 7.4374. Min Act: -0.1700
Data Index: 8119320 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19