Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.3251. Min Act: -0.1700
Data Index: 5921 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2938. Min Act: -0.1700
Data Index: 8589257 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2626. Min Act: -0.1700
Data Index: 1127638 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2313. Min Act: -0.1700
Data Index: 5791311 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2313. Min Act: -0.1700
Data Index: 1402586 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2313. Min Act: -0.1700
Data Index: 5683934 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2313. Min Act: -0.1700
Data Index: 6782629 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2001. Min Act: -0.1700
Data Index: 5982299 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2001. Min Act: -0.1700
Data Index: 7141735 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.2001. Min Act: -0.1700
Data Index: 6990074 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.1376. Min Act: -0.1700
Data Index: 5203143 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.1376. Min Act: -0.1700
Data Index: 5275702 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.1063. Min Act: -0.1700
Data Index: 6444133 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.0438. Min Act: -0.1700
Data Index: 4523452 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.0126. Min Act: -0.1700
Data Index: 5133133 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.0438. Min Act: -0.1700
Data Index: 4459608 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.0438. Min Act: -0.1700
Data Index: 5308868 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.0438. Min Act: -0.1700
Data Index: 5649153 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3251. Min Range: -6.3251
Max Act: 6.0126. Min Act: -0.1700
Data Index: 5807808 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3251. Min Range: -6.3251
Max Act: 5.9813. Min Act: -0.1700
Data Index: 4870157 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19