Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4345 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.9443. Min Act: -0.1700
Data Index: 6374720 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.8506. Min Act: -0.1700
Data Index: 1937124 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.8193. Min Act: -0.1700
Data Index: 7128582 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.7881. Min Act: -0.1700
Data Index: 1996668 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.7256. Min Act: -0.1700
Data Index: 4547398 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.7256. Min Act: -0.1700
Data Index: 4768031 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.7256. Min Act: -0.1700
Data Index: 3587578 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.7256. Min Act: -0.1700
Data Index: 7146916 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6943. Min Act: -0.1700
Data Index: 296112 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.7256. Min Act: -0.1700
Data Index: 296106 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6943. Min Act: -0.1700
Data Index: 1105464 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6943. Min Act: -0.1700
Data Index: 6903819 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6943. Min Act: -0.1700
Data Index: 3587582 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6318. Min Act: -0.1700
Data Index: 8604573 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6631. Min Act: -0.1700
Data Index: 3380484 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6631. Min Act: -0.1700
Data Index: 5982737 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6631. Min Act: -0.1700
Data Index: 894748 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6318. Min Act: -0.1700
Data Index: 4553355 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6318. Min Act: -0.1700
Data Index: 2911591 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9443. Min Range: -5.9443
Max Act: 5.6318. Min Act: -0.1700
Data Index: 3587583 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19