Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 108 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.4702. Min Act: -0.1700
Data Index: 4743367 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.4077. Min Act: -0.1700
Data Index: 4973915 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3452. Min Act: -0.1700
Data Index: 6777528 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3452. Min Act: -0.1700
Data Index: 536584 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.3452. Min Act: -0.1700
Data Index: 2127630 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2827. Min Act: -0.1700
Data Index: 5088399 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.2202. Min Act: -0.1700
Data Index: 8143973 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1889. Min Act: -0.1700
Data Index: 980994 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1889. Min Act: -0.1700
Data Index: 7835138 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1577. Min Act: -0.1700
Data Index: 6989874 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1264. Min Act: -0.1700
Data Index: 1704147 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.0952. Min Act: -0.1700
Data Index: 7577524 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1264. Min Act: -0.1700
Data Index: 6379602 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1577. Min Act: -0.1700
Data Index: 5249464 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1577. Min Act: -0.1700
Data Index: 1868869 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1264. Min Act: -0.1700
Data Index: 7661059 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.0952. Min Act: -0.1700
Data Index: 1701105 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.0952. Min Act: -0.1700
Data Index: 7777108 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.0952. Min Act: -0.1700
Data Index: 6187545 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4702. Min Range: -5.4702
Max Act: 5.1264. Min Act: -0.1700
Data Index: 3463394 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19