Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.9112. Min Act: -0.1700
Data Index: 4537674 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8800. Min Act: -0.1700
Data Index: 1482433 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8800. Min Act: -0.1700
Data Index: 113201 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8487. Min Act: -0.1700
Data Index: 4661 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8800. Min Act: -0.1700
Data Index: 5315726 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8487. Min Act: -0.1700
Data Index: 784530 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8487. Min Act: -0.1699
Data Index: 966070 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 1097759 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 3742408 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8487. Min Act: -0.1700
Data Index: 3859881 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 571132 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 5759492 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 571131 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 1432571 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 429684 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 7259025 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 2678712 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.8175. Min Act: -0.1700
Data Index: 3004922 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.7862. Min Act: -0.1700
Data Index: 3637802 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9112. Min Range: -4.9112
Max Act: 4.7862. Min Act: -0.1700
Data Index: 386302 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19