Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4562 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.7272. Min Act: -0.1700
Data Index: 95960 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.4460. Min Act: -0.1700
Data Index: 5043025 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.4772. Min Act: -0.1700
Data Index: 8798592 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.2897. Min Act: -0.1700
Data Index: 1144529 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.2272. Min Act: -0.1700
Data Index: 8551117 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1960. Min Act: -0.1700
Data Index: 6452408 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1647. Min Act: -0.1700
Data Index: 6261658 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1647. Min Act: -0.1700
Data Index: 3466885 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1960. Min Act: -0.1700
Data Index: 6535784 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1335. Min Act: -0.1700
Data Index: 5043026 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1022. Min Act: -0.1700
Data Index: 7947843 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.1022. Min Act: -0.1700
Data Index: 540411 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 828758 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.0710. Min Act: -0.1700
Data Index: 3471457 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 3578601 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.0397. Min Act: -0.1700
Data Index: 1724146 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7272. Min Range: -7.7272
Max Act: 7.0085. Min Act: -0.1700
Data Index: 6357651 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7272. Min Range: -7.7272
Max Act: 6.9772. Min Act: -0.1700
Data Index: 2050075 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7272. Min Range: -7.7272
Max Act: 6.9772. Min Act: -0.1700
Data Index: 4037896 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7272. Min Range: -7.7272
Max Act: 6.9460. Min Act: -0.1700
Data Index: 7036615 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19