Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0921. Min Range: -8.0921
Max Act: 8.0921. Min Act: -0.1700
Data Index: 4837616 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0921. Min Range: -8.0921
Max Act: 8.0296. Min Act: -0.1700
Data Index: 5638227 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.9671. Min Act: -0.1700
Data Index: 5579636 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.9358. Min Act: -0.1700
Data Index: 6433988 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.9046. Min Act: -0.1700
Data Index: 7674408 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.8733. Min Act: -0.1700
Data Index: 8311419 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.8108. Min Act: -0.1700
Data Index: 2323784 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.8421. Min Act: -0.1700
Data Index: 7870221 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.8108. Min Act: -0.1700
Data Index: 7897348 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.8108. Min Act: -0.1700
Data Index: 2465231 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.7796. Min Act: -0.1700
Data Index: 614633 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.7796. Min Act: -0.1700
Data Index: 2029741 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.7796. Min Act: -0.1700
Data Index: 2102719 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.7483. Min Act: -0.1700
Data Index: 201613 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.7171. Min Act: -0.1700
Data Index: 7776700 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.6858. Min Act: -0.1700
Data Index: 2170553 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.6858. Min Act: -0.1700
Data Index: 3441209 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.6858. Min Act: -0.1700
Data Index: 967310 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.6546. Min Act: -0.1700
Data Index: 3897875 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0921. Min Range: -8.0921
Max Act: 7.6233. Min Act: -0.1700
Data Index: 2186306 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19