Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 852 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2497. Min Range: -7.2497
Max Act: 7.2497. Min Act: -0.1700
Data Index: 7941587 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2497. Min Range: -7.2497
Max Act: 7.0310. Min Act: -0.1700
Data Index: 4597934 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.9372. Min Act: -0.1700
Data Index: 2983753 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.9060. Min Act: -0.1700
Data Index: 5174857 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.9060. Min Act: -0.1700
Data Index: 3909692 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.9060. Min Act: -0.1700
Data Index: 218329 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.8747. Min Act: -0.1700
Data Index: 3901237 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.8435. Min Act: -0.1700
Data Index: 6982647 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4348751 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.8435. Min Act: -0.1700
Data Index: 1555033 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.8122. Min Act: -0.1700
Data Index: 4206420 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.7810. Min Act: -0.1700
Data Index: 1720641 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.7497. Min Act: -0.1700
Data Index: 858469 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.7497. Min Act: -0.1700
Data Index: 29560 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.7497. Min Act: -0.1700
Data Index: 6037638 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.6872. Min Act: -0.1700
Data Index: 5543635 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.6872. Min Act: -0.1700
Data Index: 4550122 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.6560. Min Act: -0.1700
Data Index: 1206381 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.6560. Min Act: -0.1700
Data Index: 1469294 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2497. Min Range: -7.2497
Max Act: 6.6247. Min Act: -0.1700
Data Index: 6866408 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19