Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5590 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.5376. Min Act: -0.1700
Data Index: 2738035 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.3814. Min Act: -0.1700
Data Index: 8544951 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.2876. Min Act: -0.1700
Data Index: 375138 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.2251. Min Act: -0.1700
Data Index: 5153495 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.2251. Min Act: -0.1700
Data Index: 7656277 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.2251. Min Act: -0.1700
Data Index: 7656276 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1939. Min Act: -0.1700
Data Index: 2413924 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 4753622 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1626. Min Act: -0.1700
Data Index: 8053921 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 7656279 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 3565869 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 5858179 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 7312428 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 8313201 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1314. Min Act: -0.1700
Data Index: 5832688 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1001. Min Act: -0.1700
Data Index: 1727841 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1001. Min Act: -0.1700
Data Index: 4944172 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1001. Min Act: -0.1700
Data Index: 1838823 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.1001. Min Act: -0.1700
Data Index: 4898043 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5376. Min Range: -4.5376
Max Act: 4.0688. Min Act: -0.1700
Data Index: 7537045 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19