Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 767 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.2229. Min Act: -0.1700
Data Index: 8682343 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.1916. Min Act: -0.1700
Data Index: 8537051 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.1604. Min Act: -0.1700
Data Index: 7850379 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.1916. Min Act: -0.1700
Data Index: 1888297 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.1604. Min Act: -0.1700
Data Index: 7188563 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.1291. Min Act: -0.1700
Data Index: 7379273 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.0666. Min Act: -0.1700
Data Index: 1629423 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2229. Min Range: -5.2229
Max Act: 5.0666. Min Act: -0.1700
Data Index: 7512161 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9729. Min Act: -0.1700
Data Index: 6127253 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9729. Min Act: -0.1700
Data Index: 2130206 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9729. Min Act: -0.1700
Data Index: 8031012 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9416. Min Act: -0.1700
Data Index: 7479124 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9416. Min Act: -0.1700
Data Index: 4904237 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.8791. Min Act: -0.1700
Data Index: 5806164 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 308115 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 2785119 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 5818271 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 4507829 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 1149377 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2229. Min Range: -5.2229
Max Act: 4.9104. Min Act: -0.1700
Data Index: 772819 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19