Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.7246. Min Act: -0.1700
Data Index: 8664890 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.7406. Min Act: -0.1700
Data Index: 3865788 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.7246. Min Act: -0.1700
Data Index: 5646223 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.7086. Min Act: -0.1700
Data Index: 7091901 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.7086. Min Act: -0.1700
Data Index: 1571505 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6766. Min Act: -0.1700
Data Index: 3474930 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6926. Min Act: -0.1700
Data Index: 6488632 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6926. Min Act: -0.1700
Data Index: 7494111 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6926. Min Act: -0.1700
Data Index: 5321890 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6926. Min Act: -0.1700
Data Index: 1361144 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6766. Min Act: -0.1700
Data Index: 3762750 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 6293147 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 4050096 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 2751409 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6445. Min Act: -0.1700
Data Index: 6838527 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 6267784 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 6808322 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 7528527 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6606. Min Act: -0.1700
Data Index: 3327232 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7406. Min Range: -2.7406
Max Act: 2.6285. Min Act: -0.1700
Data Index: 2750783 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19