Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 470 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.5465. Min Act: -0.1700
Data Index: 6840974 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.3277. Min Act: -0.1700
Data Index: 6949973 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.2652. Min Act: -0.1700
Data Index: 6113794 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.2652. Min Act: -0.1700
Data Index: 6356623 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.2652. Min Act: -0.1700
Data Index: 5743567 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1715. Min Act: -0.1700
Data Index: 2334287 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.2027. Min Act: -0.1700
Data Index: 6470346 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.2027. Min Act: -0.1700
Data Index: 3155688 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1715. Min Act: -0.1700
Data Index: 1822720 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1402. Min Act: -0.1700
Data Index: 2486275 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1402. Min Act: -0.1700
Data Index: 2797816 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1402. Min Act: -0.1700
Data Index: 6843902 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1402. Min Act: -0.1700
Data Index: 8543599 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1090. Min Act: -0.1700
Data Index: 1882180 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1090. Min Act: -0.1700
Data Index: 5712855 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.0777. Min Act: -0.1700
Data Index: 6564280 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1090. Min Act: -0.1700
Data Index: 293154 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1090. Min Act: -0.1700
Data Index: 3737038 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1090. Min Act: -0.1700
Data Index: 6435240 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5465. Min Range: -5.5465
Max Act: 5.1090. Min Act: -0.1700
Data Index: 8683035 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19