Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 6348983 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.3007. Min Act: -0.1700
Data Index: 1586729 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.2695. Min Act: -0.1700
Data Index: 3120354 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.2070. Min Act: -0.1700
Data Index: 6699812 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.2070. Min Act: -0.1700
Data Index: 7117746 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.2070. Min Act: -0.1700
Data Index: 8461878 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.2382. Min Act: -0.1700
Data Index: 3548901 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.2070. Min Act: -0.1700
Data Index: 4241691 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1757. Min Act: -0.1700
Data Index: 3541884 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1445. Min Act: -0.1700
Data Index: 3541897 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1445. Min Act: -0.1700
Data Index: 123271 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 1493350 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 4598753 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 8361247 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 8322823 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 1047548 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 1072793 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.0820. Min Act: -0.1700
Data Index: 4849533 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.0820. Min Act: -0.1700
Data Index: 7682390 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3007. Min Range: -5.3007
Max Act: 5.1132. Min Act: -0.1700
Data Index: 2474406 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19