Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 16 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.7940. Min Act: -0.1700
Data Index: 4683953 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.7940. Min Act: -0.1700
Data Index: 4993692 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.5128. Min Act: -0.1700
Data Index: 2463114 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.4815. Min Act: -0.1700
Data Index: 4700788 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.4503. Min Act: -0.1700
Data Index: 7230013 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.4190. Min Act: -0.1700
Data Index: 3416742 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.4190. Min Act: -0.1700
Data Index: 7798839 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.4190. Min Act: -0.1700
Data Index: 1163735 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.3565. Min Act: -0.1700
Data Index: 6291601 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.3253. Min Act: -0.1700
Data Index: 8675252 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.3565. Min Act: -0.1700
Data Index: 6509470 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.3253. Min Act: -0.1700
Data Index: 6748760 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2940. Min Act: -0.1700
Data Index: 8462936 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2628. Min Act: -0.1700
Data Index: 6470571 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2628. Min Act: -0.1700
Data Index: 186691 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2628. Min Act: -0.1700
Data Index: 4395703 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2628. Min Act: -0.1700
Data Index: 3110469 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2315. Min Act: -0.1700
Data Index: 2210543 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.1690. Min Act: -0.1700
Data Index: 6094908 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7940. Min Range: -7.7940
Max Act: 7.2315. Min Act: -0.1700
Data Index: 3217006 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19