Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4773 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.3572. Min Act: -0.1700
Data Index: 7160898 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.2322. Min Act: -0.1700
Data Index: 5389577 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.1385. Min Act: -0.1700
Data Index: 5538480 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.1072. Min Act: -0.1700
Data Index: 137482 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.1072. Min Act: -0.1700
Data Index: 4133546 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.1072. Min Act: -0.1700
Data Index: 6011309 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.0447. Min Act: -0.1700
Data Index: 3034506 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.0447. Min Act: -0.1700
Data Index: 7248939 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9822. Min Act: -0.1700
Data Index: 2787455 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.0135. Min Act: -0.1700
Data Index: 4440104 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3572. Min Range: -5.3572
Max Act: 5.0135. Min Act: -0.1700
Data Index: 505342 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9510. Min Act: -0.1700
Data Index: 3211209 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9822. Min Act: -0.1700
Data Index: 93171 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9510. Min Act: -0.1700
Data Index: 5835399 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9822. Min Act: -0.1700
Data Index: 1522328 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9510. Min Act: -0.1700
Data Index: 6639170 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9510. Min Act: -0.1700
Data Index: 1627229 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9510. Min Act: -0.1700
Data Index: 7748816 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9510. Min Act: -0.1700
Data Index: 998827 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3572. Min Range: -5.3572
Max Act: 4.9197. Min Act: -0.1700
Data Index: 3210890 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19