Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.3140. Min Act: -0.1700
Data Index: 4123090 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.2515. Min Act: -0.1700
Data Index: 6340853 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.2515. Min Act: -0.1700
Data Index: 6143795 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.2515. Min Act: -0.1700
Data Index: 3403140 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.2202. Min Act: -0.1700
Data Index: 2099569 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1890. Min Act: -0.1700
Data Index: 7790998 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.2202. Min Act: -0.1700
Data Index: 5072747 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1890. Min Act: -0.1700
Data Index: 7422005 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1577. Min Act: -0.1700
Data Index: 8320658 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1577. Min Act: -0.1700
Data Index: 7997796 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1265. Min Act: -0.1700
Data Index: 5953955 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1577. Min Act: -0.1700
Data Index: 1005969 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1265. Min Act: -0.1700
Data Index: 2915483 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.1265. Min Act: -0.1700
Data Index: 8817319 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.0952. Min Act: -0.1700
Data Index: 4051813 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.0952. Min Act: -0.1700
Data Index: 3403139 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.0952. Min Act: -0.1700
Data Index: 2935009 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.0640. Min Act: -0.1700
Data Index: 1243414 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.0640. Min Act: -0.1700
Data Index: 8168277 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3140. Min Range: -4.3140
Max Act: 4.0952. Min Act: -0.1700
Data Index: 6975520 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19