Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 650 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.3012. Min Act: -0.1700
Data Index: 7188631 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.2700. Min Act: -0.1700
Data Index: 6087247 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.1450. Min Act: -0.1700
Data Index: 6566264 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.1762. Min Act: -0.1700
Data Index: 1035654 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.1137. Min Act: -0.1700
Data Index: 8090681 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.0825. Min Act: -0.1700
Data Index: 7773440 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.0200. Min Act: -0.1700
Data Index: 8093671 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.0512. Min Act: -0.1700
Data Index: 8386001 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.0512. Min Act: -0.1700
Data Index: 2048042 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3012. Min Range: -5.3012
Max Act: 5.0200. Min Act: -0.1700
Data Index: 8492221 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.9887. Min Act: -0.1700
Data Index: 4853240 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.9887. Min Act: -0.1700
Data Index: 8258414 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.9887. Min Act: -0.1700
Data Index: 905577 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.9575. Min Act: -0.1700
Data Index: 591977 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.8950. Min Act: -0.1700
Data Index: 5325205 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.8950. Min Act: -0.1700
Data Index: 5857947 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.8950. Min Act: -0.1700
Data Index: 7540748 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.8325. Min Act: -0.1700
Data Index: 7891573 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.8637. Min Act: -0.1700
Data Index: 5117379 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3012. Min Range: -5.3012
Max Act: 4.8950. Min Act: -0.1700
Data Index: 7554553 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19