Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1170 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.6231. Min Act: -0.1700
Data Index: 3428131 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.5606. Min Act: -0.1700
Data Index: 5835073 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.5293. Min Act: -0.1700
Data Index: 4228481 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.4981. Min Act: -0.1700
Data Index: 3642059 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.4668. Min Act: -0.1700
Data Index: 6076264 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.4043. Min Act: -0.1700
Data Index: 7231078 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.3731. Min Act: -0.1700
Data Index: 8104499 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.3418. Min Act: -0.1700
Data Index: 1005980 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2793. Min Act: -0.1700
Data Index: 7580556 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2481. Min Act: -0.1700
Data Index: 3440483 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2793. Min Act: -0.1700
Data Index: 2415868 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2481. Min Act: -0.1700
Data Index: 3125685 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2481. Min Act: -0.1700
Data Index: 6084960 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2481. Min Act: -0.1700
Data Index: 1539757 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.1856. Min Act: -0.1700
Data Index: 7022900 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2168. Min Act: -0.1700
Data Index: 2569785 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.2168. Min Act: -0.1700
Data Index: 633520 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.1856. Min Act: -0.1700
Data Index: 4026378 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.1543. Min Act: -0.1700
Data Index: 7359479 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6231. Min Range: -6.6231
Max Act: 6.1543. Min Act: -0.1700
Data Index: 601298 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19