Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2320 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.6414. Min Act: -0.1700
Data Index: 442429 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.6101. Min Act: -0.1700
Data Index: 7450590 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.6101. Min Act: -0.1700
Data Index: 4202823 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.6101. Min Act: -0.1700
Data Index: 7219232 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.6101. Min Act: -0.1700
Data Index: 5980894 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.6101. Min Act: -0.1700
Data Index: 3047170 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5227562 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 3176430 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 4955833 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 2171746 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 278626 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 8003662 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 3525178 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 8067300 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 4201600 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 4634082 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5788. Min Act: -0.1700
Data Index: 4251582 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5475. Min Act: -0.1700
Data Index: 3914491 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5475. Min Act: -0.1700
Data Index: 229545 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6414. Min Range: -3.6414
Max Act: 3.5475. Min Act: -0.1700
Data Index: 2614953 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19