Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 342 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.4149. Min Act: -0.1700
Data Index: 6789692 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.4149. Min Act: -0.1700
Data Index: 1663923 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.3524. Min Act: -0.1700
Data Index: 6815851 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.3524. Min Act: -0.1700
Data Index: 2071127 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.3524. Min Act: -0.1700
Data Index: 8191665 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.2274. Min Act: -0.1700
Data Index: 8578519 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1649. Min Act: -0.1700
Data Index: 6930271 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.2274. Min Act: -0.1700
Data Index: 4528535 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1024. Min Act: -0.1700
Data Index: 1691565 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1649. Min Act: -0.1700
Data Index: 8424823 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1649. Min Act: -0.1700
Data Index: 7459784 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.0399. Min Act: -0.1700
Data Index: 2472950 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1024. Min Act: -0.1700
Data Index: 4596621 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.0399. Min Act: -0.1700
Data Index: 8094796 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.0399. Min Act: -0.1700
Data Index: 6125744 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1024. Min Act: -0.1700
Data Index: 245669 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.1024. Min Act: -0.1700
Data Index: 8574470 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.0399. Min Act: -0.1700
Data Index: 948024 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4149. Min Range: -9.4149
Max Act: 9.0399. Min Act: -0.1700
Data Index: 1850606 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4149. Min Range: -9.4149
Max Act: 8.9774. Min Act: -0.1700
Data Index: 3100802 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19