Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6289 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.5013. Min Act: -0.1700
Data Index: 1107973 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.4230. Min Act: -0.1700
Data Index: 4364623 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.3132. Min Act: -0.1700
Data Index: 2415773 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.3132. Min Act: -0.1700
Data Index: 8778181 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2975. Min Act: -0.1700
Data Index: 6457114 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2818. Min Act: -0.1700
Data Index: 4396028 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2818. Min Act: -0.1700
Data Index: 6783664 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2661. Min Act: -0.1700
Data Index: 5612423 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2818. Min Act: -0.1700
Data Index: 4885602 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2503. Min Act: -0.1700
Data Index: 7565094 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2503. Min Act: -0.1700
Data Index: 8452899 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2661. Min Act: -0.1700
Data Index: 3012999 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2503. Min Act: -0.1700
Data Index: 562796 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2346. Min Act: -0.1700
Data Index: 8603149 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2503. Min Act: -0.1700
Data Index: 6113329 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2189. Min Act: -0.1700
Data Index: 5319301 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2189. Min Act: -0.1700
Data Index: 260495 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2346. Min Act: -0.1700
Data Index: 589835 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2189. Min Act: -0.1700
Data Index: 8616137 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5013. Min Range: -3.5013
Max Act: 3.2189. Min Act: -0.1700
Data Index: 4055973 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19