Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1334 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.4684. Min Act: -0.1700
Data Index: 3269523 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.4371. Min Act: -0.1700
Data Index: 36423 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.3746. Min Act: -0.1700
Data Index: 1902400 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.3121. Min Act: -0.1700
Data Index: 8044266 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.3121. Min Act: -0.1700
Data Index: 4659872 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.3121. Min Act: -0.1700
Data Index: 1233523 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2809. Min Act: -0.1700
Data Index: 8769897 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2809. Min Act: -0.1700
Data Index: 8822053 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2809. Min Act: -0.1700
Data Index: 7969801 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2496. Min Act: -0.1700
Data Index: 4167408 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2496. Min Act: -0.1700
Data Index: 144194 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2184. Min Act: -0.1700
Data Index: 773542 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2184. Min Act: -0.1700
Data Index: 6334767 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.2184. Min Act: -0.1700
Data Index: 2411868 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.1871. Min Act: -0.1700
Data Index: 1416668 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.1871. Min Act: -0.1700
Data Index: 6459967 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.1871. Min Act: -0.1700
Data Index: 7428341 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.1871. Min Act: -0.1700
Data Index: 632635 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.1871. Min Act: -0.1700
Data Index: 6829424 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4684. Min Range: -5.4684
Max Act: 5.1559. Min Act: -0.1700
Data Index: 5612484 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19