Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.4295. Min Act: -0.1700
Data Index: 142454 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.3668. Min Act: -0.1700
Data Index: 5540945 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.3197. Min Act: -0.1700
Data Index: 969536 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.2726. Min Act: -0.1700
Data Index: 7049166 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.2726. Min Act: -0.1700
Data Index: 8700062 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.2412. Min Act: -0.1700
Data Index: 1924222 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.2098. Min Act: -0.1700
Data Index: 709460 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.2255. Min Act: -0.1700
Data Index: 2273048 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.2098. Min Act: -0.1699
Data Index: 8701820 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1940. Min Act: -0.1700
Data Index: 3708101 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1626. Min Act: -0.1700
Data Index: 5371715 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1783. Min Act: -0.1700
Data Index: 475259 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1468. Min Act: -0.1700
Data Index: 7242304 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1626. Min Act: -0.1700
Data Index: 5971642 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1153. Min Act: -0.1700
Data Index: 123522 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1311. Min Act: -0.1700
Data Index: 1506617 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1468. Min Act: -0.1700
Data Index: 2762412 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.1468. Min Act: -0.1700
Data Index: 528577 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.0838. Min Act: -0.1700
Data Index: 2390209 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4295. Min Range: -3.4295
Max Act: 3.0996. Min Act: -0.1700
Data Index: 261463 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19