Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5513 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1432. Min Range: -6.1432
Max Act: 6.1432. Min Act: -0.1700
Data Index: 1956219 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.8620. Min Act: -0.1700
Data Index: 3167187 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7370. Min Act: -0.1700
Data Index: 6919969 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7370. Min Act: -0.1700
Data Index: 2962244 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.7682. Min Act: -0.1700
Data Index: 8431571 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6745. Min Act: -0.1700
Data Index: 2493726 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6745. Min Act: -0.1700
Data Index: 4991260 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.6120. Min Act: -0.1700
Data Index: 7540078 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.4870. Min Act: -0.1700
Data Index: 8157171 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.4870. Min Act: -0.1700
Data Index: 633204 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.4870. Min Act: -0.1700
Data Index: 6886385 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.4245. Min Act: -0.1700
Data Index: 633205 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.3932. Min Act: -0.1700
Data Index: 6884699 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.3620. Min Act: -0.1700
Data Index: 1734802 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.3307. Min Act: -0.1700
Data Index: 2988483 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.3307. Min Act: -0.1700
Data Index: 3284331 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.3307. Min Act: -0.1700
Data Index: 2647154 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.2995. Min Act: -0.1700
Data Index: 4854001 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.2995. Min Act: -0.1700
Data Index: 714670 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1432. Min Range: -6.1432
Max Act: 5.2995. Min Act: -0.1700
Data Index: 689890 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19