Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 755 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.8048. Min Act: -0.1700
Data Index: 3214450 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6953. Min Act: -0.1700
Data Index: 2211990 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.6484. Min Act: -0.1700
Data Index: 995504 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5858. Min Act: -0.1700
Data Index: 8246619 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5858. Min Act: -0.1700
Data Index: 1658581 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5388. Min Act: -0.1700
Data Index: 5840503 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5545. Min Act: -0.1700
Data Index: 2078727 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5075. Min Act: -0.1700
Data Index: 4463192 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5075. Min Act: -0.1700
Data Index: 8150575 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.5075. Min Act: -0.1700
Data Index: 7229929 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4919. Min Act: -0.1700
Data Index: 3219876 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4762. Min Act: -0.1700
Data Index: 1490753 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4605. Min Act: -0.1700
Data Index: 2889819 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4605. Min Act: -0.1700
Data Index: 1689494 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4605. Min Act: -0.1700
Data Index: 8705687 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3265566 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4292. Min Act: -0.1700
Data Index: 8331426 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4135. Min Act: -0.1700
Data Index: 3886024 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4135. Min Act: -0.1700
Data Index: 6221977 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8048. Min Range: -3.8048
Max Act: 3.4135. Min Act: -0.1700
Data Index: 1442017 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19