Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.7609. Min Act: -0.1700
Data Index: 1984079 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.3234. Min Act: -0.1700
Data Index: 5195270 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.3234. Min Act: -0.1700
Data Index: 7954354 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.2296. Min Act: -0.1700
Data Index: 7077654 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.1046. Min Act: -0.1700
Data Index: 3260929 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.0109. Min Act: -0.1700
Data Index: 8044018 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.0109. Min Act: -0.1700
Data Index: 3975511 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.9796. Min Act: -0.1700
Data Index: 1459680 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7609. Min Range: -6.7609
Max Act: 6.0109. Min Act: -0.1700
Data Index: 1459679 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.9796. Min Act: -0.1700
Data Index: 5233137 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.9484. Min Act: -0.1700
Data Index: 7709300 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.8859. Min Act: -0.1700
Data Index: 1179357 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.8859. Min Act: -0.1700
Data Index: 4931029 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.8546. Min Act: -0.1700
Data Index: 2693283 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.8234. Min Act: -0.1700
Data Index: 4137395 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.7921. Min Act: -0.1700
Data Index: 3760820 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.7609. Min Act: -0.1700
Data Index: 7517251 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.7609. Min Act: -0.1700
Data Index: 632052 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.7609. Min Act: -0.1700
Data Index: 6827157 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7609. Min Range: -6.7609
Max Act: 5.7609. Min Act: -0.1700
Data Index: 4542294 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19