Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.7721. Min Act: -0.1700
Data Index: 7114495 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.3346. Min Act: -0.1700
Data Index: 8782687 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.3033. Min Act: -0.1700
Data Index: 3075285 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.3033. Min Act: -0.1700
Data Index: 2887075 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.3033. Min Act: -0.1700
Data Index: 5468237 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.2721. Min Act: -0.1700
Data Index: 3764339 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.2721. Min Act: -0.1700
Data Index: 1951420 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.2408. Min Act: -0.1700
Data Index: 4157245 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.2096. Min Act: -0.1700
Data Index: 36527 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.2096. Min Act: -0.1700
Data Index: 6160410 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.1158. Min Act: -0.1700
Data Index: 8190053 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0846. Min Act: -0.1700
Data Index: 6371308 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0533. Min Act: -0.1700
Data Index: 2979495 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0533. Min Act: -0.1700
Data Index: 7667890 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0533. Min Act: -0.1700
Data Index: 5304254 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0533. Min Act: -0.1700
Data Index: 273840 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0221. Min Act: -0.1700
Data Index: 1647632 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0221. Min Act: -0.1700
Data Index: 5420388 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7721. Min Range: -6.7721
Max Act: 6.0221. Min Act: -0.1700
Data Index: 780353 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7721. Min Range: -6.7721
Max Act: 5.9908. Min Act: -0.1700
Data Index: 3381258 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19