Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5492 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1262. Min Range: -9.1262
Max Act: 9.1262. Min Act: -0.1700
Data Index: 42859 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.8762. Min Act: -0.1700
Data Index: 3294737 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.8762. Min Act: -0.1700
Data Index: 4465009 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.8137. Min Act: -0.1700
Data Index: 6343533 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.6887. Min Act: -0.1700
Data Index: 2064577 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.7512. Min Act: -0.1700
Data Index: 6797367 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.6262. Min Act: -0.1700
Data Index: 6885736 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.6262. Min Act: -0.1700
Data Index: 5935022 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5637. Min Act: -0.1700
Data Index: 4299717 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.6262. Min Act: -0.1700
Data Index: 210103 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5637. Min Act: -0.1700
Data Index: 3663487 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5637. Min Act: -0.1700
Data Index: 7084043 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5637. Min Act: -0.1700
Data Index: 8285575 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 4347668 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 38156 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 3134948 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 3268092 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 3083563 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.4387. Min Act: -0.1700
Data Index: 1469451 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1262. Min Range: -9.1262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 1224921 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19