Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 948 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.9396. Min Act: -0.1700
Data Index: 6220042 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.7521. Min Act: -0.1700
Data Index: 645920 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.7208. Min Act: -0.1700
Data Index: 5346706 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.7208. Min Act: -0.1700
Data Index: 3675259 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6896. Min Act: -0.1700
Data Index: 6815765 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6896. Min Act: -0.1700
Data Index: 8544754 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6583. Min Act: -0.1700
Data Index: 5819947 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6271. Min Act: -0.1700
Data Index: 5735950 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6583. Min Act: -0.1700
Data Index: 486727 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6583. Min Act: -0.1700
Data Index: 8544780 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6271. Min Act: -0.1700
Data Index: 6710858 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6271. Min Act: -0.1700
Data Index: 2116650 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6271. Min Act: -0.1700
Data Index: 3342901 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6271. Min Act: -0.1700
Data Index: 2594816 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.6271. Min Act: -0.1700
Data Index: 7900582 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.5958. Min Act: -0.1700
Data Index: 1450715 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.5958. Min Act: -0.1700
Data Index: 4461380 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.5958. Min Act: -0.1700
Data Index: 8538518 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.5333. Min Act: -0.1700
Data Index: 4403301 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9396. Min Range: -4.9396
Max Act: 4.5646. Min Act: -0.1700
Data Index: 3504643 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19