Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 975 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.9423. Min Act: -0.1700
Data Index: 6548327 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.7236. Min Act: -0.1700
Data Index: 1333942 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.6611. Min Act: -0.1700
Data Index: 4747808 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.5673. Min Act: -0.1700
Data Index: 1413636 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4736. Min Act: -0.1700
Data Index: 3275425 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4736. Min Act: -0.1700
Data Index: 1881927 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.5048. Min Act: -0.1700
Data Index: 1522724 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4736. Min Act: -0.1700
Data Index: 931734 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4111. Min Act: -0.1700
Data Index: 5504267 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4111. Min Act: -0.1700
Data Index: 5661786 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4111. Min Act: -0.1700
Data Index: 5735269 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.3486. Min Act: -0.1700
Data Index: 2261288 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.4111. Min Act: -0.1700
Data Index: 8027643 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.3486. Min Act: -0.1700
Data Index: 2515953 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.3486. Min Act: -0.1700
Data Index: 5735266 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.3798. Min Act: -0.1700
Data Index: 7947462 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.3486. Min Act: -0.1700
Data Index: 4438458 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.2861. Min Act: -0.1700
Data Index: 5513566 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.2861. Min Act: -0.1700
Data Index: 4494939 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9423. Min Range: -5.9423
Max Act: 5.2861. Min Act: -0.1700
Data Index: 5969263 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19