Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2543 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.9140. Min Act: -0.1700
Data Index: 2147835 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.7890. Min Act: -0.1700
Data Index: 5748696 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.5078. Min Act: -0.1700
Data Index: 5507932 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.4765. Min Act: -0.1700
Data Index: 1656203 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.5078. Min Act: -0.1700
Data Index: 5086663 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.4765. Min Act: -0.1700
Data Index: 5641732 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.4453. Min Act: -0.1700
Data Index: 665017 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.4453. Min Act: -0.1700
Data Index: 4528388 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.3828. Min Act: -0.1700
Data Index: 7421932 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.3828. Min Act: -0.1700
Data Index: 5980644 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.4140. Min Act: -0.1700
Data Index: 812285 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.3828. Min Act: -0.1700
Data Index: 64797 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.3515. Min Act: -0.1700
Data Index: 4369218 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.2890. Min Act: -0.1700
Data Index: 1237428 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.2890. Min Act: -0.1700
Data Index: 4040978 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.2890. Min Act: -0.1700
Data Index: 1043817 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.2890. Min Act: -0.1700
Data Index: 7352790 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.3203. Min Act: -0.1700
Data Index: 3952094 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.2890. Min Act: -0.1700
Data Index: 3952095 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9140. Min Range: -6.9140
Max Act: 6.3203. Min Act: -0.1700
Data Index: 6700592 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19