Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5679 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.5320. Min Act: -0.1700
Data Index: 2786704 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.4695. Min Act: -0.1700
Data Index: 5190256 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.3445. Min Act: -0.1700
Data Index: 3860724 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.3445. Min Act: -0.1700
Data Index: 1191894 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.2820. Min Act: -0.1700
Data Index: 2466997 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.2195. Min Act: -0.1700
Data Index: 303254 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.2195. Min Act: -0.1700
Data Index: 5770701 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1883. Min Act: -0.1700
Data Index: 322346 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1883. Min Act: -0.1700
Data Index: 258121 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1570. Min Act: -0.1700
Data Index: 2159072 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1570. Min Act: -0.1700
Data Index: 3343168 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1258. Min Act: -0.1700
Data Index: 2610351 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1258. Min Act: -0.1700
Data Index: 8316527 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1258. Min Act: -0.1700
Data Index: 8336877 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1258. Min Act: -0.1700
Data Index: 7763018 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.1258. Min Act: -0.1700
Data Index: 3499953 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.0945. Min Act: -0.1700
Data Index: 7554045 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.0945. Min Act: -0.1700
Data Index: 989155 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.0945. Min Act: -0.1700
Data Index: 2160075 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5320. Min Range: -6.5320
Max Act: 6.0945. Min Act: -0.1700
Data Index: 1300521 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19