Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5716 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1621. Min Range: -6.1621
Max Act: 6.1621. Min Act: -0.1700
Data Index: 2329033 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1621. Min Range: -6.1621
Max Act: 6.0059. Min Act: -0.1700
Data Index: 4956649 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3060550 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7871. Min Act: -0.1700
Data Index: 3139070 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7559. Min Act: -0.1700
Data Index: 4529551 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7246. Min Act: -0.1700
Data Index: 6902813 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7559. Min Act: -0.1700
Data Index: 657475 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7246. Min Act: -0.1700
Data Index: 4670490 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.7246. Min Act: -0.1700
Data Index: 816462 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.6309. Min Act: -0.1700
Data Index: 7066569 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.6621. Min Act: -0.1700
Data Index: 6889815 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.6309. Min Act: -0.1700
Data Index: 853400 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5684. Min Act: -0.1700
Data Index: 5240823 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5684. Min Act: -0.1700
Data Index: 7730104 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5684. Min Act: -0.1700
Data Index: 2263734 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5371. Min Act: -0.1700
Data Index: 7174274 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5371. Min Act: -0.1700
Data Index: 1563363 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5371. Min Act: -0.1700
Data Index: 1129281 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5059. Min Act: -0.1700
Data Index: 3596338 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1621. Min Range: -6.1621
Max Act: 5.5059. Min Act: -0.1700
Data Index: 4939346 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19