Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4864 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0885. Min Range: -8.0885
Max Act: 8.0885. Min Act: -0.1700
Data Index: 2735267 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.7135. Min Act: -0.1700
Data Index: 6177846 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.7135. Min Act: -0.1700
Data Index: 2591570 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.6510. Min Act: -0.1700
Data Index: 2050394 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.6823. Min Act: -0.1700
Data Index: 8053820 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.5885. Min Act: -0.1700
Data Index: 3009595 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.4323. Min Act: -0.1700
Data Index: 1061155 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.4010. Min Act: -0.1700
Data Index: 3501099 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.4010. Min Act: -0.1700
Data Index: 4967262 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2760. Min Act: -0.1700
Data Index: 6177849 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2448. Min Act: -0.1700
Data Index: 7812734 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2760. Min Act: -0.1700
Data Index: 8500981 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2448. Min Act: -0.1700
Data Index: 5257303 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2448. Min Act: -0.1700
Data Index: 8465580 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2448. Min Act: -0.1700
Data Index: 636849 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2448. Min Act: -0.1700
Data Index: 4794983 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2448. Min Act: -0.1700
Data Index: 2522065 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.1823. Min Act: -0.1700
Data Index: 6864261 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.2135. Min Act: -0.1700
Data Index: 7250253 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0885. Min Range: -8.0885
Max Act: 7.1823. Min Act: -0.1700
Data Index: 1052703 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19