Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3032 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.9707. Min Act: -0.1700
Data Index: 8274669 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.7832. Min Act: -0.1700
Data Index: 3756750 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.7520. Min Act: -0.1700
Data Index: 4439741 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.7207. Min Act: -0.1700
Data Index: 3981231 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.6582. Min Act: -0.1700
Data Index: 4485908 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.5957. Min Act: -0.1700
Data Index: 7706739 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.5957. Min Act: -0.1700
Data Index: 7298661 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.5957. Min Act: -0.1700
Data Index: 1047826 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.5332. Min Act: -0.1700
Data Index: 8122682 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.5332. Min Act: -0.1700
Data Index: 4732187 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4707. Min Act: -0.1700
Data Index: 8525265 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4707. Min Act: -0.1700
Data Index: 6113243 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4395. Min Act: -0.1700
Data Index: 2160112 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4082. Min Act: -0.1700
Data Index: 6777790 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4082. Min Act: -0.1700
Data Index: 461260 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4082. Min Act: -0.1700
Data Index: 2950789 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.4395. Min Act: -0.1700
Data Index: 1646166 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.3770. Min Act: -0.1700
Data Index: 4893784 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.3457. Min Act: -0.1700
Data Index: 5011383 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9707. Min Range: -6.9707
Max Act: 6.2832. Min Act: -0.1700
Data Index: 2857193 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19