Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4898 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0207. Min Range: -6.0207
Max Act: 6.0207. Min Act: -0.1700
Data Index: 4733213 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.6145. Min Act: -0.1700
Data Index: 6108938 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.4582. Min Act: -0.1700
Data Index: 4070250 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.4895. Min Act: -0.1700
Data Index: 5491817 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.4270. Min Act: -0.1700
Data Index: 1244221 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2357923 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.4270. Min Act: -0.1700
Data Index: 3982668 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.3645. Min Act: -0.1700
Data Index: 1235274 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.3332. Min Act: -0.1700
Data Index: 7736095 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.3332. Min Act: -0.1700
Data Index: 8083538 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.3020. Min Act: -0.1700
Data Index: 3341611 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2707. Min Act: -0.1700
Data Index: 7868164 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.3020. Min Act: -0.1700
Data Index: 4698058 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2395. Min Act: -0.1700
Data Index: 210764 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2395. Min Act: -0.1700
Data Index: 6106736 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2395. Min Act: -0.1700
Data Index: 1882152 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2082. Min Act: -0.1700
Data Index: 5690756 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2395. Min Act: -0.1700
Data Index: 3647977 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2082. Min Act: -0.1700
Data Index: 5848146 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0207. Min Range: -6.0207
Max Act: 5.2082. Min Act: -0.1700
Data Index: 6146312 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19