Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0864. Min Act: -0.1700
Data Index: 5974029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0864. Min Act: -0.1700
Data Index: 6400734 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0706. Min Act: -0.1700
Data Index: 2393579 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0706. Min Act: -0.1700
Data Index: 1247145 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0075. Min Act: -0.1700
Data Index: 6026280 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0706. Min Act: -0.1700
Data Index: 1536626 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0391. Min Act: -0.1700
Data Index: 683592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0075. Min Act: -0.1700
Data Index: 6949293 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 3276957 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0075. Min Act: -0.1700
Data Index: 4252320 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9917. Min Act: -0.1700
Data Index: 7780343 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0075. Min Act: -0.1700
Data Index: 6673075 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9917. Min Act: -0.1700
Data Index: 4182633 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0864. Min Range: -3.0864
Max Act: 3.0075. Min Act: -0.1700
Data Index: 6261751 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 2818877 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 3052148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 4792102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 4952297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 3312906 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0864. Min Range: -3.0864
Max Act: 2.9758. Min Act: -0.1700
Data Index: 3324654 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19