Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4382 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.5759. Min Act: -0.1700
Data Index: 3797992 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.3409. Min Act: -0.1700
Data Index: 441915 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.3409. Min Act: -0.1700
Data Index: 2405071 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.2467. Min Act: -0.1700
Data Index: 1967120 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.2309. Min Act: -0.1700
Data Index: 6842616 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.2152. Min Act: -0.1700
Data Index: 6245750 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.2152. Min Act: -0.1700
Data Index: 3009154 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.2152. Min Act: -0.1700
Data Index: 1735646 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1995. Min Act: -0.1700
Data Index: 1278049 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.2152. Min Act: -0.1700
Data Index: 8506201 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1838. Min Act: -0.1700
Data Index: 2716295 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1838. Min Act: -0.1700
Data Index: 5056804 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1838. Min Act: -0.1700
Data Index: 5203968 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1680. Min Act: -0.1700
Data Index: 1764432 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1680. Min Act: -0.1700
Data Index: 2843166 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1523. Min Act: -0.1700
Data Index: 8540153 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1366. Min Act: -0.1700
Data Index: 4546325 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1051. Min Act: -0.1700
Data Index: 5566487 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.1051. Min Act: -0.1700
Data Index: 2102443 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5759. Min Range: -3.5759
Max Act: 3.0893. Min Act: -0.1700
Data Index: 3900747 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19