Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5938 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.6012. Min Act: -0.1700
Data Index: 3767372 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.6012. Min Act: -0.1700
Data Index: 6149408 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.5699. Min Act: -0.1700
Data Index: 3557490 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.4449. Min Act: -0.1700
Data Index: 701658 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.4137. Min Act: -0.1700
Data Index: 934587 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.3512. Min Act: -0.1700
Data Index: 7725055 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.3512. Min Act: -0.1700
Data Index: 6153853 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.3199. Min Act: -0.1700
Data Index: 4050660 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.2887. Min Act: -0.1700
Data Index: 8609766 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.2887. Min Act: -0.1700
Data Index: 6188006 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.2887. Min Act: -0.1700
Data Index: 1210823 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.2887. Min Act: -0.1700
Data Index: 6621299 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.3199. Min Act: -0.1700
Data Index: 6431894 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.2574. Min Act: -0.1700
Data Index: 4467101 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.2262. Min Act: -0.1700
Data Index: 8523793 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.1949. Min Act: -0.1700
Data Index: 4105087 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.1949. Min Act: -0.1700
Data Index: 1021614 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.1949. Min Act: -0.1700
Data Index: 1431333 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.1637. Min Act: -0.1700
Data Index: 7084683 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6012. Min Range: -5.6012
Max Act: 5.1324. Min Act: -0.1700
Data Index: 102734 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19