Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.9460. Min Act: -0.1700
Data Index: 5567278 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.9148. Min Act: -0.1700
Data Index: 6084312 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.8523. Min Act: -0.1700
Data Index: 3171673 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.7898. Min Act: -0.1700
Data Index: 6885499 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.7273. Min Act: -0.1700
Data Index: 8818199 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.7273. Min Act: -0.1700
Data Index: 8255774 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6114325 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.6648. Min Act: -0.1700
Data Index: 2299069 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.6335. Min Act: -0.1700
Data Index: 5703156 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.6335. Min Act: -0.1700
Data Index: 1284416 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.6023. Min Act: -0.1700
Data Index: 5517553 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.5710. Min Act: -0.1700
Data Index: 3285565 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.5398. Min Act: -0.1700
Data Index: 4270322 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.5085. Min Act: -0.1700
Data Index: 3592142 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.5085. Min Act: -0.1700
Data Index: 1386576 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.4773. Min Act: -0.1700
Data Index: 2311246 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.4773. Min Act: -0.1700
Data Index: 4815392 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.4148. Min Act: -0.1700
Data Index: 4973916 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.4148. Min Act: -0.1700
Data Index: 1508352 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9460. Min Range: -5.9460
Max Act: 5.4148. Min Act: -0.1700
Data Index: 5434232 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19