Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.4936. Min Act: -0.1700
Data Index: 4674029 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.4624. Min Act: -0.1700
Data Index: 2738836 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.4311. Min Act: -0.1700
Data Index: 484520 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.3999. Min Act: -0.1700
Data Index: 2784734 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.3374. Min Act: -0.1700
Data Index: 5614479 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.3061. Min Act: -0.1700
Data Index: 6230087 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.3061. Min Act: -0.1700
Data Index: 1021276 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.3061. Min Act: -0.1700
Data Index: 5883681 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.2436. Min Act: -0.1700
Data Index: 3040839 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.2124. Min Act: -0.1700
Data Index: 2774742 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.2124. Min Act: -0.1700
Data Index: 5431589 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.1499. Min Act: -0.1700
Data Index: 2979303 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.1811. Min Act: -0.1700
Data Index: 7467277 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.1499. Min Act: -0.1700
Data Index: 6517134 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.1499. Min Act: -0.1700
Data Index: 1908505 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.0874. Min Act: -0.1700
Data Index: 4672600 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.0874. Min Act: -0.1700
Data Index: 2530344 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.0874. Min Act: -0.1700
Data Index: 1596245 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.0874. Min Act: -0.1700
Data Index: 8424032 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4936. Min Range: -5.4936
Max Act: 5.0874. Min Act: -0.1700
Data Index: 6561138 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19