Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.6158. Min Act: -0.1700
Data Index: 5781810 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.5533. Min Act: -0.1700
Data Index: 7948048 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.4908. Min Act: -0.1700
Data Index: 2508285 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.4595. Min Act: -0.1700
Data Index: 7408740 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.3345. Min Act: -0.1700
Data Index: 977743 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.3345. Min Act: -0.1700
Data Index: 7377129 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.3345. Min Act: -0.1700
Data Index: 7906711 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2720. Min Act: -0.1700
Data Index: 6499133 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2720. Min Act: -0.1700
Data Index: 8167955 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2720. Min Act: -0.1700
Data Index: 5935626 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2408. Min Act: -0.1700
Data Index: 8081330 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2408. Min Act: -0.1700
Data Index: 1192575 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2408. Min Act: -0.1700
Data Index: 4692805 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2095. Min Act: -0.1700
Data Index: 6931447 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2095. Min Act: -0.1700
Data Index: 2920532 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.2095. Min Act: -0.1700
Data Index: 8794388 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.1783. Min Act: -0.1700
Data Index: 1418809 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.1783. Min Act: -0.1700
Data Index: 5150865 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.1783. Min Act: -0.1700
Data Index: 203150 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6158. Min Range: -5.6158
Max Act: 5.1783. Min Act: -0.1700
Data Index: 5462394 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19