Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4583 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0907. Min Range: -4.0907
Max Act: 4.0907. Min Act: -0.1700
Data Index: 2753211 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0907. Min Range: -4.0907
Max Act: 4.0595. Min Act: -0.1700
Data Index: 7350820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.9657. Min Act: -0.1700
Data Index: 754454 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.9344. Min Act: -0.1700
Data Index: 1801206 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.9344. Min Act: -0.1700
Data Index: 6362811 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.9032. Min Act: -0.1700
Data Index: 4936862 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8719. Min Act: -0.1700
Data Index: 5935240 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8719. Min Act: -0.1700
Data Index: 5229330 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8719. Min Act: -0.1700
Data Index: 8720073 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8719. Min Act: -0.1700
Data Index: 7416323 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8719. Min Act: -0.1700
Data Index: 4936890 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.9032. Min Act: -0.1700
Data Index: 1754021 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8719. Min Act: -0.1700
Data Index: 6530951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8406. Min Act: -0.1700
Data Index: 5122197 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8406. Min Act: -0.1700
Data Index: 6250091 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8094. Min Act: -0.1700
Data Index: 5685081 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8406. Min Act: -0.1700
Data Index: 5431462 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.7781. Min Act: -0.1700
Data Index: 5116091 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.8094. Min Act: -0.1700
Data Index: 8386718 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0907. Min Range: -4.0907
Max Act: 3.7781. Min Act: -0.1700
Data Index: 976542 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19