Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 204 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.3570. Min Act: -0.1700
Data Index: 4791077 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2945. Min Act: -0.1700
Data Index: 5972255 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2632. Min Act: -0.1700
Data Index: 36031 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2945. Min Act: -0.1700
Data Index: 5800626 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 4099311 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2632. Min Act: -0.1700
Data Index: 1251284 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2632. Min Act: -0.1700
Data Index: 2695884 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2632. Min Act: -0.1700
Data Index: 8170863 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 3351889 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 871558 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 3809603 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2007. Min Act: -0.1700
Data Index: 731143 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 3342495 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 4248006 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2007. Min Act: -0.1700
Data Index: 2127878 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2007. Min Act: -0.1700
Data Index: 3393012 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2007. Min Act: -0.1700
Data Index: 5591923 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2007. Min Act: -0.1700
Data Index: 4329196 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2007. Min Act: -0.1700
Data Index: 51372 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3570. Min Range: -5.3570
Max Act: 5.2320. Min Act: -0.1700
Data Index: 3257271 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19