Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 425 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2957. Min Range: -6.2957
Max Act: 6.2957. Min Act: -0.1700
Data Index: 2632709 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2957. Min Range: -6.2957
Max Act: 6.1707. Min Act: -0.1700
Data Index: 786504 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2957. Min Range: -6.2957
Max Act: 6.0457. Min Act: -0.1700
Data Index: 4161276 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.9207. Min Act: -0.1700
Data Index: 3014240 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8894. Min Act: -0.1700
Data Index: 3644728 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8894. Min Act: -0.1700
Data Index: 2606532 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8894. Min Act: -0.1700
Data Index: 6134808 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8894. Min Act: -0.1700
Data Index: 4313518 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8582. Min Act: -0.1700
Data Index: 479378 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8894. Min Act: -0.1700
Data Index: 2245775 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8894. Min Act: -0.1700
Data Index: 3087949 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8582. Min Act: -0.1700
Data Index: 7448021 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8269. Min Act: -0.1700
Data Index: 811571 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.8269. Min Act: -0.1700
Data Index: 3906638 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.7957. Min Act: -0.1700
Data Index: 8005087 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.7957. Min Act: -0.1700
Data Index: 8233076 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.7644. Min Act: -0.1700
Data Index: 721768 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.7644. Min Act: -0.1700
Data Index: 6678755 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.7957. Min Act: -0.1700
Data Index: 3569736 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2957. Min Range: -6.2957
Max Act: 5.7644. Min Act: -0.1700
Data Index: 8314940 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19