Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3845 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.7131. Min Act: -0.1700
Data Index: 3833435 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.5569. Min Act: -0.1700
Data Index: 2112519 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.3694. Min Act: -0.1700
Data Index: 1462660 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.3694. Min Act: -0.1700
Data Index: 2876040 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.3694. Min Act: -0.1700
Data Index: 3503377 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.3694. Min Act: -0.1700
Data Index: 4702247 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.2444. Min Act: -0.1700
Data Index: 4587170 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.2131. Min Act: -0.1700
Data Index: 912302 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1819. Min Act: -0.1700
Data Index: 5978294 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1819. Min Act: -0.1700
Data Index: 8072684 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1819. Min Act: -0.1700
Data Index: 6155447 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1506. Min Act: -0.1700
Data Index: 4677923 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1506. Min Act: -0.1700
Data Index: 6800395 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1506. Min Act: -0.1700
Data Index: 5138620 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1194. Min Act: -0.1700
Data Index: 2905232 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1194. Min Act: -0.1700
Data Index: 8295017 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.0881. Min Act: -0.1700
Data Index: 7226531 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.1194. Min Act: -0.1700
Data Index: 1438676 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.0881. Min Act: -0.1700
Data Index: 5257262 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7131. Min Range: -6.7131
Max Act: 6.0569. Min Act: -0.1700
Data Index: 6411290 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19