Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.8458. Min Act: -0.1700
Data Index: 2248172 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.6895. Min Act: -0.1700
Data Index: 4448231 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.6895. Min Act: -0.1700
Data Index: 2929379 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.6895. Min Act: -0.1700
Data Index: 6067059 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.7208. Min Act: -0.1700
Data Index: 8374282 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.6895. Min Act: -0.1700
Data Index: 1423447 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.6270. Min Act: -0.1700
Data Index: 6343862 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.6270. Min Act: -0.1700
Data Index: 7291806 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.5958. Min Act: -0.1700
Data Index: 3760117 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.5333. Min Act: -0.1700
Data Index: 2962710 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.5645. Min Act: -0.1700
Data Index: 8257507 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.5333. Min Act: -0.1700
Data Index: 6403309 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.5020. Min Act: -0.1700
Data Index: 5579440 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.4395. Min Act: -0.1700
Data Index: 752382 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.4395. Min Act: -0.1700
Data Index: 6558269 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.4395. Min Act: -0.1700
Data Index: 5112708 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.4395. Min Act: -0.1700
Data Index: 6681242 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.4395. Min Act: -0.1700
Data Index: 3935773 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.4395. Min Act: -0.1700
Data Index: 1473119 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8458. Min Range: -5.8458
Max Act: 5.3770. Min Act: -0.1700
Data Index: 4352653 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19