Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.9326. Min Act: -0.1700
Data Index: 1217644 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.7138. Min Act: -0.1700
Data Index: 7779604 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.6201. Min Act: -0.1700
Data Index: 6635235 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.6201. Min Act: -0.1700
Data Index: 3830077 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.5576. Min Act: -0.1700
Data Index: 3859034 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.5263. Min Act: -0.1700
Data Index: 3055368 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4951. Min Act: -0.1700
Data Index: 8665897 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4638. Min Act: -0.1700
Data Index: 4983500 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.5263. Min Act: -0.1700
Data Index: 3474348 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4951. Min Act: -0.1700
Data Index: 1650107 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4951. Min Act: -0.1700
Data Index: 336407 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4951. Min Act: -0.1700
Data Index: 4734112 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4638. Min Act: -0.1700
Data Index: 4929517 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4326. Min Act: -0.1700
Data Index: 1610649 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4326. Min Act: -0.1700
Data Index: 8341501 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4013. Min Act: -0.1700
Data Index: 4185435 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4013. Min Act: -0.1700
Data Index: 378930 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.4013. Min Act: -0.1700
Data Index: 310567 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.3701. Min Act: -0.1700
Data Index: 3226131 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9326. Min Range: -5.9326
Max Act: 5.3701. Min Act: -0.1700
Data Index: 7000625 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19