Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.3687. Min Act: -0.1700
Data Index: 6614348 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.2437. Min Act: -0.1700
Data Index: 508087 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.2125. Min Act: -0.1700
Data Index: 7436009 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.1500. Min Act: -0.1700
Data Index: 7688300 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.1500. Min Act: -0.1700
Data Index: 3615020 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.0562. Min Act: -0.1700
Data Index: 4432357 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.0250. Min Act: -0.1700
Data Index: 902812 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9937. Min Act: -0.1700
Data Index: 6019112 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.0250. Min Act: -0.1700
Data Index: 1299563 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.0250. Min Act: -0.1700
Data Index: 5505318 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3687. Min Range: -5.3687
Max Act: 5.0250. Min Act: -0.1700
Data Index: 8436953 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9937. Min Act: -0.1700
Data Index: 1949621 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9937. Min Act: -0.1700
Data Index: 6130271 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9625. Min Act: -0.1700
Data Index: 7958760 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9625. Min Act: -0.1700
Data Index: 7839528 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9625. Min Act: -0.1700
Data Index: 2159770 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9625. Min Act: -0.1700
Data Index: 2442968 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9625. Min Act: -0.1700
Data Index: 8289475 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9625. Min Act: -0.1700
Data Index: 610183 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3687. Min Range: -5.3687
Max Act: 4.9312. Min Act: -0.1700
Data Index: 5196104 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19