Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1873 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.7270. Min Act: -0.1700
Data Index: 5020436 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.6645. Min Act: -0.1700
Data Index: 2935423 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.4770. Min Act: -0.1700
Data Index: 5057915 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.3520. Min Act: -0.1700
Data Index: 7924205 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.1645. Min Act: -0.1700
Data Index: 1169029 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.1020. Min Act: -0.1700
Data Index: 3811553 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.0395. Min Act: -0.1700
Data Index: 8728428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7270. Min Range: -9.7270
Max Act: 9.0395. Min Act: -0.1700
Data Index: 7181150 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.9145. Min Act: -0.1700
Data Index: 3934000 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.8520. Min Act: -0.1700
Data Index: 2303286 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.8520. Min Act: -0.1700
Data Index: 4809507 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.9145. Min Act: -0.1700
Data Index: 1320556 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.9145. Min Act: -0.1700
Data Index: 7110555 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.9145. Min Act: -0.1700
Data Index: 6711297 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.9145. Min Act: -0.1700
Data Index: 4850120 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.8520. Min Act: -0.1700
Data Index: 6607703 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.8520. Min Act: -0.1700
Data Index: 432689 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.8520. Min Act: -0.1700
Data Index: 1339569 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.7895. Min Act: -0.1700
Data Index: 5401788 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7270. Min Range: -9.7270
Max Act: 8.7895. Min Act: -0.1700
Data Index: 7134367 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19