Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4261 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.9070. Min Act: -0.1700
Data Index: 4927744 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.8445. Min Act: -0.1700
Data Index: 3606654 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.7350. Min Act: -0.1700
Data Index: 8022603 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.7037. Min Act: -0.1700
Data Index: 2862530 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.7037. Min Act: -0.1700
Data Index: 1821902 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6881. Min Act: -0.1700
Data Index: 4466902 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.7037. Min Act: -0.1700
Data Index: 8361316 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6724. Min Act: -0.1700
Data Index: 6386394 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6724. Min Act: -0.1700
Data Index: 3343010 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6724. Min Act: -0.1700
Data Index: 5834602 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6255. Min Act: -0.1700
Data Index: 113560 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6411. Min Act: -0.1700
Data Index: 3356624 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6411. Min Act: -0.1700
Data Index: 6419594 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6255. Min Act: -0.1700
Data Index: 4022357 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.6098. Min Act: -0.1700
Data Index: 4462259 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.5942. Min Act: -0.1700
Data Index: 5148209 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.5942. Min Act: -0.1700
Data Index: 699748 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.5785. Min Act: -0.1700
Data Index: 5568480 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.5785. Min Act: -0.1700
Data Index: 4648185 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9070. Min Range: -3.9070
Max Act: 3.5785. Min Act: -0.1700
Data Index: 8609124 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19