Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2793 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.5407. Min Act: -0.1700
Data Index: 8816194 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.5250. Min Act: -0.1700
Data Index: 1980763 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.4937. Min Act: -0.1700
Data Index: 593948 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.5094. Min Act: -0.1700
Data Index: 4105469 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.4780. Min Act: -0.1700
Data Index: 5901265 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.4154. Min Act: -0.1700
Data Index: 8163250 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3997. Min Act: -0.1700
Data Index: 8643961 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3840. Min Act: -0.1700
Data Index: 4840082 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3997. Min Act: -0.1700
Data Index: 3273673 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3683. Min Act: -0.1700
Data Index: 5276064 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3683. Min Act: -0.1700
Data Index: 525283 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3369. Min Act: -0.1700
Data Index: 4907429 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3369. Min Act: -0.1700
Data Index: 2270808 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3526. Min Act: -0.1700
Data Index: 318342 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3369. Min Act: -0.1700
Data Index: 4710573 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3369. Min Act: -0.1700
Data Index: 7789840 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3369. Min Act: -0.1700
Data Index: 6661774 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3526. Min Act: -0.1700
Data Index: 5365729 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3369. Min Act: -0.1700
Data Index: 4476553 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5407. Min Range: -3.5407
Max Act: 3.3212. Min Act: -0.1700
Data Index: 5790442 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19