Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2718 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.9399. Min Act: -0.1688
Data Index: 5538542 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.9399. Min Act: -0.1700
Data Index: 3638693 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.9087. Min Act: -0.1700
Data Index: 6461374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.9087. Min Act: -0.1700
Data Index: 7895722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.9087. Min Act: -0.1700
Data Index: 8646099 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8774. Min Act: -0.1700
Data Index: 5409255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8774. Min Act: -0.1700
Data Index: 4400149 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8462. Min Act: -0.1700
Data Index: 2836775 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8462. Min Act: -0.1700
Data Index: 877261 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8149. Min Act: -0.1700
Data Index: 4018746 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8462. Min Act: -0.1700
Data Index: 7317664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8149. Min Act: -0.1699
Data Index: 7842351 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8149. Min Act: -0.1700
Data Index: 448964 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.8149. Min Act: -0.1700
Data Index: 8078684 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7837. Min Act: -0.1700
Data Index: 1986593 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7524. Min Act: -0.1700
Data Index: 3669481 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7524. Min Act: -0.1700
Data Index: 6665322 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7524. Min Act: -0.1700
Data Index: 7326166 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7524. Min Act: -0.1700
Data Index: 4806484 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9399. Min Range: -4.9399
Max Act: 4.7524. Min Act: -0.1700
Data Index: 477691 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19