Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0684. Min Range: -5.0684
Max Act: 5.0684. Min Act: -0.1700
Data Index: 3709661 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0684. Min Range: -5.0684
Max Act: 5.0059. Min Act: -0.1700
Data Index: 8634588 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.7872. Min Act: -0.1700
Data Index: 857362 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.7872. Min Act: -0.1700
Data Index: 650706 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.7247. Min Act: -0.1700
Data Index: 6146653 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.6934. Min Act: -0.1700
Data Index: 1626708 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.6622. Min Act: -0.1700
Data Index: 3975539 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.6309. Min Act: -0.1700
Data Index: 3256174 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.6309. Min Act: -0.1700
Data Index: 1889819 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5997. Min Act: -0.1700
Data Index: 383460 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5997. Min Act: -0.1700
Data Index: 6935056 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5997. Min Act: -0.1700
Data Index: 1626706 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5684. Min Act: -0.1700
Data Index: 2719753 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5997. Min Act: -0.1700
Data Index: 17218 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5684. Min Act: -0.1700
Data Index: 6080757 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5372. Min Act: -0.1700
Data Index: 1626705 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5372. Min Act: -0.1700
Data Index: 4483658 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5059. Min Act: -0.1700
Data Index: 5716839 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5372. Min Act: -0.1700
Data Index: 1889806 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0684. Min Range: -5.0684
Max Act: 4.5372. Min Act: -0.1700
Data Index: 8481230 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19