Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2493 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.6220. Min Act: -0.1700
Data Index: 1159040 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.5908. Min Act: -0.1700
Data Index: 8596056 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5480452 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.5283. Min Act: -0.1700
Data Index: 3059923 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4658. Min Act: -0.1700
Data Index: 4604039 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4345. Min Act: -0.1700
Data Index: 3763515 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4032. Min Act: -0.1700
Data Index: 2299138 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4032. Min Act: -0.1700
Data Index: 408775 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4032. Min Act: -0.1700
Data Index: 4060929 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4032. Min Act: -0.1700
Data Index: 5224486 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.4032. Min Act: -0.1700
Data Index: 7275379 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3407. Min Act: -0.1700
Data Index: 2807178 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3407. Min Act: -0.1700
Data Index: 7338631 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3407. Min Act: -0.1700
Data Index: 1337169 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3407. Min Act: -0.1700
Data Index: 7225927 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3407. Min Act: -0.1700
Data Index: 3671920 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3095. Min Act: -0.1700
Data Index: 338327 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3095. Min Act: -0.1700
Data Index: 1389430 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.3095. Min Act: -0.1700
Data Index: 2419336 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6220. Min Range: -4.6220
Max Act: 4.2782. Min Act: -0.1700
Data Index: 2100111 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19