Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5409 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.9650. Min Act: -0.1700
Data Index: 2521324 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6837. Min Act: -0.1700
Data Index: 2536326 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6837. Min Act: -0.1700
Data Index: 4464245 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6525. Min Act: -0.1700
Data Index: 7313794 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.6212. Min Act: -0.1700
Data Index: 328953 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.5275. Min Act: -0.1700
Data Index: 8464054 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 6635763 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 8120172 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 6752678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 900947 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 3844397 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 5589403 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 4792851 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 508492 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 7856515 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 8801110 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1698
Data Index: 7731407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4337. Min Act: -0.1700
Data Index: 3096066 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4650. Min Act: -0.1700
Data Index: 4290691 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9650. Min Range: -5.9650
Max Act: 5.4337. Min Act: -0.1700
Data Index: 7319004 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19