Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3453. Min Act: -0.1700
Data Index: 8073915 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3140. Min Act: -0.1700
Data Index: 3260162 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.3140. Min Act: -0.1700
Data Index: 5343365 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2828. Min Act: -0.1700
Data Index: 1878964 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2515. Min Act: -0.1700
Data Index: 3974075 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2515. Min Act: -0.1700
Data Index: 8770542 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2515. Min Act: -0.1700
Data Index: 590623 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2515. Min Act: -0.1700
Data Index: 5357449 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.2203. Min Act: -0.1700
Data Index: 5703096 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1890. Min Act: -0.1700
Data Index: 7065807 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 7420944 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1890. Min Act: -0.1700
Data Index: 3491933 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1890. Min Act: -0.1700
Data Index: 8171961 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 4259310 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1578. Min Act: -0.1700
Data Index: 263942 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.0953. Min Act: -0.1700
Data Index: 1379435 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 4960762 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5034495 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 6097093 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3453. Min Range: -5.3453
Max Act: 5.1265. Min Act: -0.1700
Data Index: 5462452 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19