Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1458 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.6953. Min Act: -0.1700
Data Index: 1326500 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.6640. Min Act: -0.1700
Data Index: 7312887 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.6014. Min Act: -0.1700
Data Index: 2810755 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.6171. Min Act: -0.1700
Data Index: 7579943 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5858. Min Act: -0.1700
Data Index: 2221536 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.6014. Min Act: -0.1700
Data Index: 1875595 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5858. Min Act: -0.1700
Data Index: 1212506 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5858. Min Act: -0.1700
Data Index: 955026 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5858. Min Act: -0.1700
Data Index: 7578314 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5858. Min Act: -0.1700
Data Index: 6194295 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5858. Min Act: -0.1700
Data Index: 7578315 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5701. Min Act: -0.1700
Data Index: 6708872 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5701. Min Act: -0.1700
Data Index: 7293761 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5701. Min Act: -0.1700
Data Index: 2222534 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5701. Min Act: -0.1700
Data Index: 7631893 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5545. Min Act: -0.1700
Data Index: 5153047 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5545. Min Act: -0.1700
Data Index: 2739141 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5545. Min Act: -0.1700
Data Index: 1484588 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5545. Min Act: -0.1700
Data Index: 4699797 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6953. Min Range: -3.6953
Max Act: 3.5545. Min Act: -0.1700
Data Index: 4810001 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19