Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.9149. Min Act: -0.1700
Data Index: 1097886 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.8524. Min Act: -0.1700
Data Index: 7801688 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.7899. Min Act: -0.1700
Data Index: 5066874 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.7899. Min Act: -0.1700
Data Index: 460381 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.7274. Min Act: -0.1700
Data Index: 190359 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.6337. Min Act: -0.1700
Data Index: 8740172 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.6649. Min Act: -0.1700
Data Index: 7129374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7569552 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.6337. Min Act: -0.1700
Data Index: 7684614 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.5712. Min Act: -0.1700
Data Index: 576158 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.5712. Min Act: -0.1700
Data Index: 8078920 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.5399. Min Act: -0.1700
Data Index: 8122134 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.5087. Min Act: -0.1700
Data Index: 4144088 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4774. Min Act: -0.1700
Data Index: 2364874 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4774. Min Act: -0.1700
Data Index: 1468785 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4462. Min Act: -0.1700
Data Index: 3999849 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4462. Min Act: -0.1700
Data Index: 4113242 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4462. Min Act: -0.1700
Data Index: 6076971 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4149. Min Act: -0.1700
Data Index: 6520553 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9149. Min Range: -5.9149
Max Act: 5.4462. Min Act: -0.1700
Data Index: 7090131 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19