Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.2965. Min Act: -0.1700
Data Index: 820935 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1715. Min Act: -0.1700
Data Index: 3572675 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1403. Min Act: -0.1700
Data Index: 7683177 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1403. Min Act: -0.1700
Data Index: 2599269 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1090. Min Act: -0.1700
Data Index: 991343 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1403. Min Act: -0.1700
Data Index: 7095911 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1090. Min Act: -0.1700
Data Index: 879878 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.1090. Min Act: -0.1700
Data Index: 1480091 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0778. Min Act: -0.1700
Data Index: 589884 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0465. Min Act: -0.1700
Data Index: 6710214 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0778. Min Act: -0.1700
Data Index: 648081 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0778. Min Act: -0.1700
Data Index: 6970465 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0778. Min Act: -0.1700
Data Index: 8541728 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0465. Min Act: -0.1700
Data Index: 3260487 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0153. Min Act: -0.1700
Data Index: 4429713 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0465. Min Act: -0.1700
Data Index: 6842733 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0465. Min Act: -0.1700
Data Index: 8406521 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0153. Min Act: -0.1700
Data Index: 1366241 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2965. Min Range: -5.2965
Max Act: 5.0153. Min Act: -0.1700
Data Index: 4100145 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2965. Min Range: -5.2965
Max Act: 4.9840. Min Act: -0.1700
Data Index: 6934990 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19