Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5236 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.5592. Min Act: -0.1700
Data Index: 4772248 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.4655. Min Act: -0.1700
Data Index: 3283937 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.4342. Min Act: -0.1700
Data Index: 3261381 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.3717. Min Act: -0.1700
Data Index: 3930731 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.3405. Min Act: -0.1700
Data Index: 8122563 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.3405. Min Act: -0.1700
Data Index: 2575934 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.3405. Min Act: -0.1700
Data Index: 8018841 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.3405. Min Act: -0.1700
Data Index: 2234960 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2780. Min Act: -0.1700
Data Index: 3688638 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2780. Min Act: -0.1700
Data Index: 7107724 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2467. Min Act: -0.1700
Data Index: 2629633 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2467. Min Act: -0.1700
Data Index: 3514196 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2467. Min Act: -0.1700
Data Index: 2173982 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2155. Min Act: -0.1700
Data Index: 7587605 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.2155. Min Act: -0.1700
Data Index: 7123041 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.1842. Min Act: -0.1700
Data Index: 5767653 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.1842. Min Act: -0.1700
Data Index: 6652572 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.1842. Min Act: -0.1700
Data Index: 7045728 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.1530. Min Act: -0.1700
Data Index: 2249887 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5592. Min Range: -7.5592
Max Act: 7.1530. Min Act: -0.1700
Data Index: 2615225 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19