Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 271 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0900. Min Range: -7.0900
Max Act: 7.0900. Min Act: -0.1700
Data Index: 6307892 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.9650. Min Act: -0.1700
Data Index: 849525 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.9650. Min Act: -0.1700
Data Index: 920704 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.9650. Min Act: -0.1700
Data Index: 3189013 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.7775. Min Act: -0.1700
Data Index: 2732357 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.6213. Min Act: -0.1700
Data Index: 3215475 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.6213. Min Act: -0.1700
Data Index: 7134054 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.6213. Min Act: -0.1700
Data Index: 3744236 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.5900. Min Act: -0.1700
Data Index: 5091985 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.6213. Min Act: -0.1700
Data Index: 6604425 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.5900. Min Act: -0.1700
Data Index: 1538180 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4963. Min Act: -0.1700
Data Index: 6812387 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4963. Min Act: -0.1700
Data Index: 2374313 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4963. Min Act: -0.1700
Data Index: 8185898 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4338. Min Act: -0.1700
Data Index: 7189780 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4650. Min Act: -0.1700
Data Index: 1527253 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4338. Min Act: -0.1700
Data Index: 3927365 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4338. Min Act: -0.1700
Data Index: 5373574 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4338. Min Act: -0.1700
Data Index: 829804 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0900. Min Range: -7.0900
Max Act: 6.4338. Min Act: -0.1700
Data Index: 1729689 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19