Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2268 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1157. Min Range: -6.1157
Max Act: 6.1157. Min Act: -0.1700
Data Index: 231530 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.4907. Min Act: -0.1700
Data Index: 4298845 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.5532. Min Act: -0.1700
Data Index: 8634713 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.4907. Min Act: -0.1700
Data Index: 7214463 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.4282. Min Act: -0.1700
Data Index: 4054761 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.4282. Min Act: -0.1700
Data Index: 5946174 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3969. Min Act: -0.1700
Data Index: 606159 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3657. Min Act: -0.1700
Data Index: 5269394 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3344. Min Act: -0.1700
Data Index: 6610714 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3344. Min Act: -0.1700
Data Index: 1353253 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 7307710 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 6487039 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 1407488 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 3104526 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 2093919 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 2556266 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.2719. Min Act: -0.1700
Data Index: 7487 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.3032. Min Act: -0.1700
Data Index: 6188855 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.2719. Min Act: -0.1700
Data Index: 1781156 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1157. Min Range: -6.1157
Max Act: 5.2719. Min Act: -0.1700
Data Index: 5716515 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19