Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3744. Min Range: -7.3744
Max Act: 7.3744. Min Act: -0.1700
Data Index: 333851 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.7494. Min Act: -0.1700
Data Index: 5257510 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.6869. Min Act: -0.1700
Data Index: 3874806 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.5619. Min Act: -0.1700
Data Index: 4571756 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.4369. Min Act: -0.1700
Data Index: 5363008 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.4057. Min Act: -0.1700
Data Index: 2116924 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.3744. Min Act: -0.1700
Data Index: 5226843 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.3744. Min Act: -0.1700
Data Index: 7075204 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.3432. Min Act: -0.1700
Data Index: 7928990 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.3432. Min Act: -0.1700
Data Index: 6232207 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.3119. Min Act: -0.1700
Data Index: 5980283 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.2807. Min Act: -0.1700
Data Index: 2078314 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 1244870 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.1557. Min Act: -0.1700
Data Index: 2764060 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.1557. Min Act: -0.1700
Data Index: 1443146 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 7956317 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.1244. Min Act: -0.1700
Data Index: 5391418 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.0932. Min Act: -0.1700
Data Index: 5650072 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.0932. Min Act: -0.1700
Data Index: 2666269 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3744. Min Range: -7.3744
Max Act: 6.0619. Min Act: -0.1700
Data Index: 4933110 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19