Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.2494. Min Act: -0.1700
Data Index: 6203650 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1997. Min Act: -0.1700
Data Index: 4089314 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.1331. Min Act: -0.1700
Data Index: 1434215 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0997. Min Act: -0.1700
Data Index: 2954397 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0997. Min Act: -0.1700
Data Index: 6731348 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0830. Min Act: -0.1700
Data Index: 5929587 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0662. Min Act: -0.1659
Data Index: 6525103 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0662. Min Act: -0.1700
Data Index: 1140451 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0494. Min Act: -0.1700
Data Index: 4290759 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0494. Min Act: -0.1700
Data Index: 1500106 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0662. Min Act: -0.1700
Data Index: 5340260 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0325. Min Act: -0.1700
Data Index: 4884768 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0325. Min Act: -0.1700
Data Index: 5517964 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0325. Min Act: -0.1700
Data Index: 3339054 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0325. Min Act: -0.1700
Data Index: 5331171 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0325. Min Act: -0.1700
Data Index: 5669759 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0157. Min Act: -0.1700
Data Index: 7244939 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0157. Min Act: -0.1700
Data Index: 872912 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2494. Min Range: -2.2494
Max Act: 1.9988. Min Act: -0.1700
Data Index: 4774995 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2494. Min Range: -2.2494
Max Act: 2.0157. Min Act: -0.1700
Data Index: 1193689 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19