Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2568 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.6089. Min Act: -0.1700
Data Index: 5635126 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.5464. Min Act: -0.1700
Data Index: 6783744 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.5151. Min Act: -0.1700
Data Index: 7639425 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.4839. Min Act: -0.1700
Data Index: 69689 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.5151. Min Act: -0.1700
Data Index: 2274906 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.4839. Min Act: -0.1700
Data Index: 8814951 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.4214. Min Act: -0.1700
Data Index: 8192686 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.3901. Min Act: -0.1700
Data Index: 5494189 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.3276. Min Act: -0.1700
Data Index: 2496847 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2651. Min Act: -0.1700
Data Index: 3969548 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2651. Min Act: -0.1700
Data Index: 6619964 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2651. Min Act: -0.1700
Data Index: 4417812 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2651. Min Act: -0.1700
Data Index: 2434522 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2651. Min Act: -0.1700
Data Index: 966052 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2651. Min Act: -0.1700
Data Index: 591984 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2339. Min Act: -0.1700
Data Index: 6997707 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2339. Min Act: -0.1700
Data Index: 1840788 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2339. Min Act: -0.1700
Data Index: 6674421 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2026. Min Act: -0.1700
Data Index: 387861 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6089. Min Range: -5.6089
Max Act: 5.2339. Min Act: -0.1700
Data Index: 2731020 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19