Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3530 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0418. Min Range: -3.0418
Max Act: 3.0418. Min Act: -0.1700
Data Index: 1381280 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9786. Min Act: -0.1700
Data Index: 2532043 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9786. Min Act: -0.1700
Data Index: 5323430 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9628. Min Act: -0.1700
Data Index: 7439549 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9628. Min Act: -0.1700
Data Index: 1521624 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9470. Min Act: -0.1700
Data Index: 3110048 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9311. Min Act: -0.1700
Data Index: 1551012 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9153. Min Act: -0.1700
Data Index: 3016209 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9153. Min Act: -0.1700
Data Index: 4913295 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 8560472 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9153. Min Act: -0.1700
Data Index: 8455047 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 8486324 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 3993644 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 2697527 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 8472405 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 3881255 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 4016376 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 1870285 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 3117489 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 5473364 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19