Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2135 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.8709. Min Act: -0.1700
Data Index: 2498585 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.8550. Min Act: -0.1700
Data Index: 8413771 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.8232. Min Act: -0.1700
Data Index: 1703292 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.7755. Min Act: -0.1700
Data Index: 1921288 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.7116. Min Act: -0.1700
Data Index: 6812912 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.7276. Min Act: -0.1700
Data Index: 4943425 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6956. Min Act: -0.1700
Data Index: 8395338 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.7436. Min Act: -0.1700
Data Index: 1193561 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.7116. Min Act: -0.1700
Data Index: 6901315 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6956. Min Act: -0.1700
Data Index: 3887529 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6796. Min Act: -0.1700
Data Index: 3553519 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6796. Min Act: -0.1700
Data Index: 7666756 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6635. Min Act: -0.1700
Data Index: 4775090 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6635. Min Act: -0.1700
Data Index: 4102205 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6475. Min Act: -0.1700
Data Index: 660809 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6475. Min Act: -0.1700
Data Index: 4573191 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6154. Min Act: -0.1700
Data Index: 5342111 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6475. Min Act: -0.1700
Data Index: 5026873 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6475. Min Act: -0.1700
Data Index: 445709 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8709. Min Range: -2.8709
Max Act: 2.6475. Min Act: -0.1700
Data Index: 4888605 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19