Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1633 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.4150. Min Act: -0.1700
Data Index: 2574686 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.3525. Min Act: -0.1700
Data Index: 5600 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.2900. Min Act: -0.1700
Data Index: 5191272 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.2900. Min Act: -0.1700
Data Index: 5203109 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.2588. Min Act: -0.1700
Data Index: 8089592 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.2588. Min Act: -0.1700
Data Index: 2156860 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.2275. Min Act: -0.1700
Data Index: 4405376 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1963. Min Act: -0.1700
Data Index: 1472980 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1963. Min Act: -0.1700
Data Index: 2493508 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1963. Min Act: -0.1700
Data Index: 2717532 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1963. Min Act: -0.1700
Data Index: 6566889 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1650. Min Act: -0.1700
Data Index: 432752 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1650. Min Act: -0.1700
Data Index: 4090890 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1650. Min Act: -0.1700
Data Index: 1907 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1338. Min Act: -0.1700
Data Index: 7251498 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1338. Min Act: -0.1700
Data Index: 8415403 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1338. Min Act: -0.1700
Data Index: 7778194 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1338. Min Act: -0.1700
Data Index: 2385245 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1025. Min Act: -0.1700
Data Index: 7255164 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4150. Min Range: -4.4150
Max Act: 4.1025. Min Act: -0.1700
Data Index: 4177175 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19