Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.3893. Min Act: -0.1700
Data Index: 8654541 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.3580. Min Act: -0.1700
Data Index: 2796948 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.2955. Min Act: -0.1700
Data Index: 2874287 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.2018. Min Act: -0.1700
Data Index: 5414377 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.2018. Min Act: -0.1700
Data Index: 868213 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.1393. Min Act: -0.1700
Data Index: 5993963 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.1705. Min Act: -0.1700
Data Index: 1095519 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.1393. Min Act: -0.1700
Data Index: 873632 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.1080. Min Act: -0.1700
Data Index: 6639692 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0768. Min Act: -0.1700
Data Index: 84520 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 1819176 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 1506204 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 1061983 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 3159273 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 7811445 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 4758632 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0143. Min Act: -0.1700
Data Index: 5976225 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0143. Min Act: -0.1700
Data Index: 4855621 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3893. Min Range: -7.3893
Max Act: 6.9830. Min Act: -0.1700
Data Index: 1681592 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3893. Min Range: -7.3893
Max Act: 7.0455. Min Act: -0.1700
Data Index: 6611245 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19