Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 420 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.8991. Min Act: -0.1700
Data Index: 8338224 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.8991. Min Act: -0.1700
Data Index: 5640048 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.8991. Min Act: -0.1700
Data Index: 5874494 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.8366. Min Act: -0.1700
Data Index: 4448429 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.8053. Min Act: -0.1700
Data Index: 3432806 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.7428. Min Act: -0.1700
Data Index: 3049626 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.6803. Min Act: -0.1700
Data Index: 2884032 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.7116. Min Act: -0.1700
Data Index: 3661765 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.6178. Min Act: -0.1700
Data Index: 735350 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.6491. Min Act: -0.1700
Data Index: 7518756 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.6178. Min Act: -0.1700
Data Index: 1392660 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.5866. Min Act: -0.1700
Data Index: 958573 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.5866. Min Act: -0.1700
Data Index: 4330109 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.5241. Min Act: -0.1700
Data Index: 5250160 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.5241. Min Act: -0.1700
Data Index: 2103175 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.4928. Min Act: -0.1700
Data Index: 8391023 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.4303. Min Act: -0.1700
Data Index: 1935277 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.4616. Min Act: -0.1700
Data Index: 958865 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.4303. Min Act: -0.1700
Data Index: 1135416 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8991. Min Range: -7.8991
Max Act: 7.4303. Min Act: -0.1700
Data Index: 1035916 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19