Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.0262. Min Range: -16.0262
Max Act: 16.0262. Min Act: -0.1700
Data Index: 2730807 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.7762. Min Act: -0.1700
Data Index: 4661894 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.9012. Min Act: -0.1700
Data Index: 4250405 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.7762. Min Act: -0.1700
Data Index: 750290 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.6512. Min Act: -0.1700
Data Index: 6503555 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.4012. Min Act: -0.1700
Data Index: 8388287 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.4012. Min Act: -0.1700
Data Index: 2780116 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.4012. Min Act: -0.1700
Data Index: 6934830 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2762. Min Act: -0.1700
Data Index: 7746200 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2762. Min Act: -0.1700
Data Index: 2730804 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2762. Min Act: -0.1700
Data Index: 4334751 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2762. Min Act: -0.1700
Data Index: 6591732 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2762. Min Act: -0.1700
Data Index: 6591733 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2137. Min Act: -0.1700
Data Index: 3287809 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.2137. Min Act: -0.1700
Data Index: 1949306 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.1512. Min Act: -0.1700
Data Index: 7452645 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.1512. Min Act: -0.1700
Data Index: 2730802 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.1512. Min Act: -0.1700
Data Index: 1949302 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.0887. Min Act: -0.1700
Data Index: 6591746 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.0262. Min Range: -16.0262
Max Act: 15.0887. Min Act: -0.1700
Data Index: 2730805 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19