Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.5314. Min Act: -0.1700
Data Index: 3336764 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.5314. Min Act: -0.1700
Data Index: 2279286 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.5314. Min Act: -0.1700
Data Index: 1289397 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.4064. Min Act: -0.1700
Data Index: 4668037 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.3439. Min Act: -0.1700
Data Index: 5738023 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.2814. Min Act: -0.1700
Data Index: 4072414 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.2814. Min Act: -0.1700
Data Index: 196109 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.2189. Min Act: -0.1700
Data Index: 3814769 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.2189. Min Act: -0.1700
Data Index: 7106723 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.1564. Min Act: -0.1700
Data Index: 6840629 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.1564. Min Act: -0.1700
Data Index: 2611035 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.1564. Min Act: -0.1700
Data Index: 7828166 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0939. Min Act: -0.1700
Data Index: 100132 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0939. Min Act: -0.1700
Data Index: 5991478 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0314. Min Act: -0.1700
Data Index: 8723973 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0314. Min Act: -0.1700
Data Index: 7869233 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0314. Min Act: -0.1700
Data Index: 6666728 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0314. Min Act: -0.1700
Data Index: 72650 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0314. Min Act: -0.1700
Data Index: 3626415 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5314. Min Range: -9.5314
Max Act: 9.0939. Min Act: -0.1700
Data Index: 3410003 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19