Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2504 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1906. Min Range: -8.1906
Max Act: 8.1906. Min Act: -0.1700
Data Index: 438009 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1906. Min Range: -8.1906
Max Act: 8.1906. Min Act: -0.1700
Data Index: 2896388 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1906. Min Range: -8.1906
Max Act: 8.1281. Min Act: -0.1700
Data Index: 8824270 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1906. Min Range: -8.1906
Max Act: 8.0031. Min Act: -0.1700
Data Index: 3770935 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.9406. Min Act: -0.1700
Data Index: 2175516 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8781. Min Act: -0.1700
Data Index: 5459572 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.9406. Min Act: -0.1700
Data Index: 2206613 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8781. Min Act: -0.1700
Data Index: 6208913 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8781. Min Act: -0.1700
Data Index: 1024641 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.7531. Min Act: -0.1700
Data Index: 4620817 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8156. Min Act: -0.1700
Data Index: 2139248 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8156. Min Act: -0.1700
Data Index: 4042991 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8156. Min Act: -0.1700
Data Index: 6702352 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8156. Min Act: -0.1700
Data Index: 17087 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8156. Min Act: -0.1700
Data Index: 565190 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.8156. Min Act: -0.1700
Data Index: 1482093 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.7531. Min Act: -0.1700
Data Index: 4069807 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.7531. Min Act: -0.1700
Data Index: 1803334 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.7218. Min Act: -0.1700
Data Index: 6595896 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1906. Min Range: -8.1906
Max Act: 7.7218. Min Act: -0.1700
Data Index: 5318584 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19