Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1435 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.3599. Min Act: -0.1700
Data Index: 4048287 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.2662. Min Act: -0.1700
Data Index: 285606 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.2662. Min Act: -0.1700
Data Index: 7037624 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.2037. Min Act: -0.1700
Data Index: 6486412 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.1724. Min Act: -0.1700
Data Index: 5962032 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.1411. Min Act: -0.1700
Data Index: 6415771 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.1724. Min Act: -0.1700
Data Index: 7801792 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.1099. Min Act: -0.1700
Data Index: 993206 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3390411 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0786. Min Act: -0.1700
Data Index: 989688 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.1099. Min Act: -0.1700
Data Index: 2474662 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0474. Min Act: -0.1700
Data Index: 2717064 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 7791566 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 838135 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 5054197 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 1367489 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3599. Min Range: -4.3599
Max Act: 3.9849. Min Act: -0.1700
Data Index: 4381249 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 6682492 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 389443 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3599. Min Range: -4.3599
Max Act: 4.0161. Min Act: -0.1700
Data Index: 964402 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19