Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1167 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.2086. Min Act: -0.1700
Data Index: 8450196 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.1771. Min Act: -0.1700
Data Index: 3645727 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.1771. Min Act: -0.1700
Data Index: 759513 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.1456. Min Act: -0.1700
Data Index: 7301164 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.1456. Min Act: -0.1700
Data Index: 5190227 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0984. Min Act: -0.1700
Data Index: 2078069 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0826. Min Act: -0.1700
Data Index: 3289573 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0669. Min Act: -0.1700
Data Index: 8580184 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0669. Min Act: -0.1700
Data Index: 1108621 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0353. Min Act: -0.1700
Data Index: 5186485 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0511. Min Act: -0.1700
Data Index: 851351 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0037. Min Act: -0.1700
Data Index: 2812418 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0037. Min Act: -0.1700
Data Index: 219126 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0195. Min Act: -0.1700
Data Index: 5282856 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0195. Min Act: -0.1700
Data Index: 4415180 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0195. Min Act: -0.1700
Data Index: 8403943 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0037. Min Act: -0.1700
Data Index: 651553 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2086. Min Range: -3.2086
Max Act: 3.0037. Min Act: -0.1700
Data Index: 1315169 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2086. Min Range: -3.2086
Max Act: 2.9721. Min Act: -0.1700
Data Index: 6583199 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2086. Min Range: -3.2086
Max Act: 2.9563. Min Act: -0.1700
Data Index: 4404491 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19