Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6111 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8743. Min Act: -0.1700
Data Index: 6930044 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8585. Min Act: -0.1700
Data Index: 2914614 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8585. Min Act: -0.1700
Data Index: 6575486 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8426. Min Act: -0.1700
Data Index: 5657258 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8426. Min Act: -0.1700
Data Index: 1123796 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8585. Min Act: -0.1700
Data Index: 6462827 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8426. Min Act: -0.1700
Data Index: 785874 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8267. Min Act: -0.1700
Data Index: 6189760 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8267. Min Act: -0.1700
Data Index: 3890464 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8267. Min Act: -0.1700
Data Index: 2042546 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8267. Min Act: -0.1700
Data Index: 4228871 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.7948. Min Act: -0.1700
Data Index: 5680292 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8108. Min Act: -0.1700
Data Index: 6957642 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8108. Min Act: -0.1700
Data Index: 1092568 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8108. Min Act: -0.1700
Data Index: 4406478 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8108. Min Act: -0.1700
Data Index: 4744902 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8108. Min Act: -0.1700
Data Index: 2446042 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8108. Min Act: -0.1700
Data Index: 2603630 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.8267. Min Act: -0.1700
Data Index: 1351815 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8743. Min Range: -2.8743
Max Act: 2.7948. Min Act: -0.1700
Data Index: 7520211 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19