Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1648 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2313. Min Range: -6.2313
Max Act: 6.2313. Min Act: -0.1700
Data Index: 5966418 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 8602912 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.7313. Min Act: -0.1700
Data Index: 1251170 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.5750. Min Act: -0.1700
Data Index: 902943 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.6063. Min Act: -0.1700
Data Index: 8631484 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.4500. Min Act: -0.1700
Data Index: 6875943 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.4500. Min Act: -0.1700
Data Index: 4737428 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.4188. Min Act: -0.1700
Data Index: 2388838 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.3563. Min Act: -0.1700
Data Index: 5337701 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.3250. Min Act: -0.1700
Data Index: 2757184 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2938. Min Act: -0.1700
Data Index: 6788530 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2938. Min Act: -0.1700
Data Index: 3870198 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2625. Min Act: -0.1700
Data Index: 5180614 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2313. Min Act: -0.1700
Data Index: 8371703 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2000. Min Act: -0.1700
Data Index: 8445108 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2000. Min Act: -0.1700
Data Index: 279982 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2000. Min Act: -0.1700
Data Index: 177264 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.2000. Min Act: -0.1700
Data Index: 2049064 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.1688. Min Act: -0.1700
Data Index: 6515274 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2313. Min Range: -6.2313
Max Act: 5.1688. Min Act: -0.1700
Data Index: 1876032 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19