Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1487 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0095. Min Range: -6.0095
Max Act: 6.0095. Min Act: -0.1700
Data Index: 2619232 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.9470. Min Act: -0.1700
Data Index: 7227911 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.9158. Min Act: -0.1700
Data Index: 2505489 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.8845. Min Act: -0.1700
Data Index: 441364 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7595. Min Act: -0.1700
Data Index: 6848799 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7595. Min Act: -0.1700
Data Index: 4582985 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7595. Min Act: -0.1700
Data Index: 1958036 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.7283. Min Act: -0.1700
Data Index: 2651766 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6970. Min Act: -0.1700
Data Index: 8029112 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6658. Min Act: -0.1700
Data Index: 3188894 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6658. Min Act: -0.1700
Data Index: 5222238 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6345. Min Act: -0.1700
Data Index: 3347275 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6658. Min Act: -0.1700
Data Index: 3558185 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6345. Min Act: -0.1700
Data Index: 2404923 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6033. Min Act: -0.1700
Data Index: 6804119 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6033. Min Act: -0.1700
Data Index: 7052107 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6033. Min Act: -0.1700
Data Index: 5445064 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6033. Min Act: -0.1700
Data Index: 6196150 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6033. Min Act: -0.1700
Data Index: 3993496 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0095. Min Range: -6.0095
Max Act: 5.6033. Min Act: -0.1700
Data Index: 6516008 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19