Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.6208. Min Act: -0.1700
Data Index: 3891071 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.6208. Min Act: -0.1700
Data Index: 3796214 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.5583. Min Act: -0.1700
Data Index: 8362507 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.5583. Min Act: -0.1700
Data Index: 4915925 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.4958. Min Act: -0.1700
Data Index: 7004417 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.4333. Min Act: -0.1700
Data Index: 4737657 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.3396. Min Act: -0.1700
Data Index: 8152842 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.3396. Min Act: -0.1700
Data Index: 944519 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.2771. Min Act: -0.1700
Data Index: 7936814 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6170501 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.2146. Min Act: -0.1700
Data Index: 5476169 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.2146. Min Act: -0.1700
Data Index: 7383919 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1521. Min Act: -0.1700
Data Index: 4333854 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1521. Min Act: -0.1700
Data Index: 171376 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1833. Min Act: -0.1700
Data Index: 4028877 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1179825 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1521. Min Act: -0.1700
Data Index: 624123 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1833. Min Act: -0.1700
Data Index: 1937737 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1521. Min Act: -0.1700
Data Index: 7065577 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6208. Min Range: -5.6208
Max Act: 5.1208. Min Act: -0.1700
Data Index: 6060363 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19