Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5569 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.6519. Min Act: -0.1700
Data Index: 3720948 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.3394. Min Act: -0.1700
Data Index: 3151759 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.2456. Min Act: -0.1700
Data Index: 458667 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.2456. Min Act: -0.1700
Data Index: 6180159 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1519. Min Act: -0.1700
Data Index: 1187010 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1519. Min Act: -0.1700
Data Index: 7238810 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1519. Min Act: -0.1700
Data Index: 2712088 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1519. Min Act: -0.1700
Data Index: 769888 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1206. Min Act: -0.1700
Data Index: 3767714 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1519. Min Act: -0.1700
Data Index: 7135615 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1206. Min Act: -0.1700
Data Index: 3086465 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1206. Min Act: -0.1700
Data Index: 330305 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.1206. Min Act: -0.1700
Data Index: 3765473 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2562046 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0894. Min Act: -0.1700
Data Index: 769896 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2199545 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0894. Min Act: -0.1700
Data Index: 22403 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0581. Min Act: -0.1700
Data Index: 5936547 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0581. Min Act: -0.1700
Data Index: 2777590 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6519. Min Range: -5.6519
Max Act: 5.0894. Min Act: -0.1700
Data Index: 769882 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19