Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2856. Min Range: -8.2856
Max Act: 8.2856. Min Act: -0.1700
Data Index: 2029448 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2856. Min Range: -8.2856
Max Act: 8.0356. Min Act: -0.1700
Data Index: 4754261 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.9418. Min Act: -0.1700
Data Index: 5513755 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.8168. Min Act: -0.1700
Data Index: 1866841 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.7543. Min Act: -0.1700
Data Index: 6027446 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.6918. Min Act: -0.1700
Data Index: 7726245 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.6606. Min Act: -0.1700
Data Index: 814551 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5981. Min Act: -0.1700
Data Index: 5770006 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5981. Min Act: -0.1700
Data Index: 73461 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5668. Min Act: -0.1700
Data Index: 1346315 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5356. Min Act: -0.1700
Data Index: 5638027 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5043. Min Act: -0.1700
Data Index: 5405109 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5043. Min Act: -0.1700
Data Index: 3137072 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5043. Min Act: -0.1700
Data Index: 1584910 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5043. Min Act: -0.1700
Data Index: 6130732 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5043. Min Act: -0.1700
Data Index: 5585321 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.5043. Min Act: -0.1700
Data Index: 1640323 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.4418. Min Act: -0.1700
Data Index: 2256951 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.4418. Min Act: -0.1700
Data Index: 2025142 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2856. Min Range: -8.2856
Max Act: 7.4731. Min Act: -0.1700
Data Index: 4608248 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19