Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 553 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.4845. Min Act: -0.1700
Data Index: 6694529 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.4845. Min Act: -0.1700
Data Index: 4124482 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.4845. Min Act: -0.1700
Data Index: 4688793 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.4532. Min Act: -0.1700
Data Index: 8561234 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.4220. Min Act: -0.1700
Data Index: 8187748 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.4220. Min Act: -0.1700
Data Index: 2283689 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3907. Min Act: -0.1700
Data Index: 6738959 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 6014338 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3907. Min Act: -0.1700
Data Index: 8264782 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3907. Min Act: -0.1700
Data Index: 272434 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3907. Min Act: -0.1700
Data Index: 178717 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3907. Min Act: -0.1700
Data Index: 3494860 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 6924912 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 3997555 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3282. Min Act: -0.1700
Data Index: 181541 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 605644 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 3838223 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 5135356 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 5419289 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4845. Min Range: -4.4845
Max Act: 4.3595. Min Act: -0.1700
Data Index: 451068 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19