Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4250 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.9131. Min Act: -0.1700
Data Index: 5332555 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.6631. Min Act: -0.1700
Data Index: 7379120 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.3506. Min Act: -0.1700
Data Index: 2460383 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.2881. Min Act: -0.1700
Data Index: 1701154 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.2256. Min Act: -0.1700
Data Index: 8087231 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1631. Min Act: -0.1700
Data Index: 3650957 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1944. Min Act: -0.1700
Data Index: 5324753 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1631. Min Act: -0.1700
Data Index: 7953813 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1631. Min Act: -0.1700
Data Index: 5711285 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1319. Min Act: -0.1700
Data Index: 2603766 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1319. Min Act: -0.1700
Data Index: 418691 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.1006. Min Act: -0.1700
Data Index: 8768110 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.0694. Min Act: -0.1700
Data Index: 6798357 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 418690 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 5227877 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9131. Min Range: -7.9131
Max Act: 7.0069. Min Act: -0.1700
Data Index: 7510509 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9131. Min Range: -7.9131
Max Act: 6.9756. Min Act: -0.1700
Data Index: 7435721 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9131. Min Range: -7.9131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 42770 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9131. Min Range: -7.9131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 2724093 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9131. Min Range: -7.9131
Max Act: 6.9131. Min Act: -0.1700
Data Index: 5603470 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19