Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.4410. Min Act: -0.1700
Data Index: 7188481 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.3785. Min Act: -0.1700
Data Index: 4511107 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.3785. Min Act: -0.1700
Data Index: 1828852 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.3160. Min Act: -0.1700
Data Index: 2317372 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.2535. Min Act: -0.1700
Data Index: 2548351 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.2223. Min Act: -0.1700
Data Index: 4327080 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.2223. Min Act: -0.1700
Data Index: 6367960 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.1910. Min Act: -0.1700
Data Index: 7778431 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.1910. Min Act: -0.1700
Data Index: 482607 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.1598. Min Act: -0.1700
Data Index: 1155498 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.1285. Min Act: -0.1700
Data Index: 7640 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.1285. Min Act: -0.1700
Data Index: 2863608 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.1285. Min Act: -0.1700
Data Index: 994898 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.0973. Min Act: -0.1700
Data Index: 2548350 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.0660. Min Act: -0.1700
Data Index: 710962 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.0035. Min Act: -0.1700
Data Index: 7087503 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.0035. Min Act: -0.1700
Data Index: 7318900 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4410. Min Range: -6.4410
Max Act: 6.0035. Min Act: -0.1700
Data Index: 7696438 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4410. Min Range: -6.4410
Max Act: 5.9723. Min Act: -0.1700
Data Index: 1644802 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4410. Min Range: -6.4410
Max Act: 5.9723. Min Act: -0.1700
Data Index: 2546658 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19