Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5868 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1768. Min Range: -6.1768
Max Act: 6.1768. Min Act: -0.1700
Data Index: 4667910 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1768. Min Range: -6.1768
Max Act: 6.0206. Min Act: -0.1700
Data Index: 2926282 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.8956. Min Act: -0.1700
Data Index: 4361983 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.8643. Min Act: -0.1700
Data Index: 4913016 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.8643. Min Act: -0.1700
Data Index: 483899 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.7393. Min Act: -0.1700
Data Index: 1520224 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.7393. Min Act: -0.1700
Data Index: 7675950 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.7081. Min Act: -0.1700
Data Index: 5147355 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6768. Min Act: -0.1700
Data Index: 4986175 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6768. Min Act: -0.1700
Data Index: 7651823 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.7081. Min Act: -0.1700
Data Index: 2568734 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6456. Min Act: -0.1700
Data Index: 5905986 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6456. Min Act: -0.1700
Data Index: 829343 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6456. Min Act: -0.1700
Data Index: 7156743 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6456. Min Act: -0.1700
Data Index: 8399959 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6143. Min Act: -0.1700
Data Index: 6845330 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6143. Min Act: -0.1700
Data Index: 1311459 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6143. Min Act: -0.1700
Data Index: 5684954 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6143. Min Act: -0.1700
Data Index: 3695910 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1768. Min Range: -6.1768
Max Act: 5.6456. Min Act: -0.1700
Data Index: 8325886 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19