Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 889 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.5995. Min Act: -0.1700
Data Index: 5420051 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.5370. Min Act: -0.1700
Data Index: 6888363 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.3495. Min Act: -0.1700
Data Index: 6395747 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.3183. Min Act: -0.1700
Data Index: 6213137 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.2870. Min Act: -0.1700
Data Index: 2597310 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.3183. Min Act: -0.1700
Data Index: 5804538 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.2558. Min Act: -0.1700
Data Index: 2560479 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.1933. Min Act: -0.1700
Data Index: 1281326 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.1933. Min Act: -0.1700
Data Index: 5173115 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.1933. Min Act: -0.1700
Data Index: 5134501 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.1620. Min Act: -0.1700
Data Index: 4015836 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.1308. Min Act: -0.1700
Data Index: 7420447 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 5270872 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 4380469 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 6535634 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 8163203 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0683. Min Act: -0.1700
Data Index: 7744300 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 2014939 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 7008704 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5995. Min Range: -5.5995
Max Act: 5.0683. Min Act: -0.1700
Data Index: 4258830 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19