Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.5800. Min Act: -0.1700
Data Index: 132879 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.2675. Min Act: -0.1700
Data Index: 2468302 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.1425. Min Act: -0.1700
Data Index: 4267980 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.0175. Min Act: -0.1700
Data Index: 4439971 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5800. Min Range: -6.5800
Max Act: 6.0175. Min Act: -0.1700
Data Index: 326157 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.9550. Min Act: -0.1700
Data Index: 3766037 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8925. Min Act: -0.1700
Data Index: 834514 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.9237. Min Act: -0.1700
Data Index: 1862803 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.9550. Min Act: -0.1700
Data Index: 2960604 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4159234 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8612. Min Act: -0.1700
Data Index: 7692733 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8612. Min Act: -0.1700
Data Index: 244547 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8300. Min Act: -0.1700
Data Index: 7977672 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8300. Min Act: -0.1700
Data Index: 4766788 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8612. Min Act: -0.1700
Data Index: 2048776 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.8300. Min Act: -0.1700
Data Index: 1475885 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.7987. Min Act: -0.1700
Data Index: 2047940 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.7987. Min Act: -0.1700
Data Index: 1501747 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.7987. Min Act: -0.1700
Data Index: 1985601 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5800. Min Range: -6.5800
Max Act: 5.7675. Min Act: -0.1700
Data Index: 1284065 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19