Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4439 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1952. Min Range: -5.1952
Max Act: 5.1952. Min Act: -0.1700
Data Index: 1574423 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1952. Min Range: -5.1952
Max Act: 5.1639. Min Act: -0.1700
Data Index: 8229891 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1952. Min Range: -5.1952
Max Act: 5.0702. Min Act: -0.1700
Data Index: 5225359 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1952. Min Range: -5.1952
Max Act: 5.0389. Min Act: -0.1700
Data Index: 6765762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1952. Min Range: -5.1952
Max Act: 5.0389. Min Act: -0.1700
Data Index: 6962530 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1952. Min Range: -5.1952
Max Act: 5.0077. Min Act: -0.1700
Data Index: 573495 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.9452. Min Act: -0.1700
Data Index: 2232209 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.9139. Min Act: -0.1700
Data Index: 2514554 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.9139. Min Act: -0.1700
Data Index: 5086121 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8827. Min Act: -0.1700
Data Index: 5980863 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.9139. Min Act: -0.1700
Data Index: 5039912 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8827. Min Act: -0.1700
Data Index: 566759 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8827. Min Act: -0.1700
Data Index: 4706332 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8514. Min Act: -0.1700
Data Index: 5783775 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8202. Min Act: -0.1700
Data Index: 4942341 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8202. Min Act: -0.1700
Data Index: 1617742 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8202. Min Act: -0.1700
Data Index: 1329532 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.8202. Min Act: -0.1700
Data Index: 1941683 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.7889. Min Act: -0.1700
Data Index: 3145501 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1952. Min Range: -5.1952
Max Act: 4.7889. Min Act: -0.1700
Data Index: 1070881 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19