Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2609 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.5237. Min Act: -0.1700
Data Index: 5753015 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.5237. Min Act: -0.1697
Data Index: 5319038 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.4924. Min Act: -0.1700
Data Index: 2560133 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.4610. Min Act: -0.1700
Data Index: 2054864 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3983. Min Act: -0.1700
Data Index: 7075952 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3983. Min Act: -0.1700
Data Index: 7683414 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3826. Min Act: -0.1700
Data Index: 3035781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3983. Min Act: -0.1700
Data Index: 6124083 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3983. Min Act: -0.1698
Data Index: 5319037 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3826. Min Act: -0.1700
Data Index: 5559515 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3826. Min Act: -0.1700
Data Index: 2854766 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3513. Min Act: -0.1700
Data Index: 4852630 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3513. Min Act: -0.1700
Data Index: 7636885 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3513. Min Act: -0.1700
Data Index: 5208069 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3513. Min Act: -0.1700
Data Index: 6227297 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3513. Min Act: -0.1694
Data Index: 2054860 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3199. Min Act: -0.1693
Data Index: 5319035 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3199. Min Act: -0.1700
Data Index: 6707342 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3042. Min Act: -0.1700
Data Index: 1034109 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5237. Min Range: -3.5237
Max Act: 3.3042. Min Act: -0.1700
Data Index: 3815374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19