Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1020. Min Range: -2.1020
Max Act: 2.1020. Min Act: -0.1504
Data Index: 7229895 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1020. Min Range: -2.1020
Max Act: 2.0768. Min Act: -0.1413
Data Index: 8665283 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1020. Min Range: -2.1020
Max Act: 2.0179. Min Act: -0.1344
Data Index: 7971902 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9926. Min Act: -0.0524
Data Index: 6332889 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1020. Min Range: -2.1020
Max Act: 2.0179. Min Act: -0.1434
Data Index: 7095369 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9841. Min Act: -0.1590
Data Index: 4098641 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9587. Min Act: -0.0905
Data Index: 4971048 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9587. Min Act: -0.1169
Data Index: 7658869 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9502. Min Act: -0.1606
Data Index: 5704244 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9587. Min Act: -0.1480
Data Index: 2756504 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9502. Min Act: -0.1199
Data Index: 3617845 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9332. Min Act: -0.1510
Data Index: 7284091 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9332. Min Act: -0.1486
Data Index: 7256875 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9417. Min Act: -0.1474
Data Index: 2027919 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9332. Min Act: -0.1553
Data Index: 6081370 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9332. Min Act: -0.1344
Data Index: 8478008 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9332. Min Act: -0.1084
Data Index: 7197174 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9332. Min Act: -0.1310
Data Index: 2057233 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9247. Min Act: -0.1209
Data Index: 2992520 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1020. Min Range: -2.1020
Max Act: 1.9247. Min Act: -0.1247
Data Index: 1064923 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19