Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4437 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.6699. Min Act: -0.1700
Data Index: 6740550 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3887. Min Act: -0.1700
Data Index: 3394152 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3574. Min Act: -0.1700
Data Index: 6406655 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3887. Min Act: -0.1700
Data Index: 4942449 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3887. Min Act: -0.1700
Data Index: 8746808 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3574. Min Act: -0.1700
Data Index: 8820301 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3262. Min Act: -0.1700
Data Index: 2566515 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.3262. Min Act: -0.1700
Data Index: 7611276 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2637. Min Act: -0.1700
Data Index: 1456270 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2949. Min Act: -0.1700
Data Index: 8763988 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2324. Min Act: -0.1700
Data Index: 7942501 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2324. Min Act: -0.1700
Data Index: 1696924 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2012. Min Act: -0.1700
Data Index: 1374431 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2012. Min Act: -0.1700
Data Index: 2592385 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.1699. Min Act: -0.1700
Data Index: 7279754 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2324. Min Act: -0.1700
Data Index: 8113501 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2012. Min Act: -0.1700
Data Index: 7863943 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2012. Min Act: -0.1700
Data Index: 2374225 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.2012. Min Act: -0.1700
Data Index: 3990309 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6699. Min Range: -6.6699
Max Act: 6.1699. Min Act: -0.1700
Data Index: 4817787 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19