Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7493. Min Range: -6.7493
Max Act: 6.7493. Min Act: -0.1700
Data Index: 3306694 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7493. Min Range: -6.7493
Max Act: 6.2181. Min Act: -0.1700
Data Index: 8014550 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7493. Min Range: -6.7493
Max Act: 6.1243. Min Act: -0.1700
Data Index: 6591632 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7493. Min Range: -6.7493
Max Act: 6.0931. Min Act: -0.1700
Data Index: 1051138 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7493. Min Range: -6.7493
Max Act: 6.0618. Min Act: -0.1700
Data Index: 129225 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7493. Min Range: -6.7493
Max Act: 6.0618. Min Act: -0.1700
Data Index: 1811339 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.9056. Min Act: -0.1700
Data Index: 4356505 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.8743. Min Act: -0.1700
Data Index: 4979008 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.8431. Min Act: -0.1700
Data Index: 6032052 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.8431. Min Act: -0.1700
Data Index: 4071357 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7806. Min Act: -0.1700
Data Index: 1036102 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.8118. Min Act: -0.1700
Data Index: 3275051 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7806. Min Act: -0.1700
Data Index: 5392083 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7493. Min Act: -0.1700
Data Index: 6019092 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7181. Min Act: -0.1700
Data Index: 1562024 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7806. Min Act: -0.1700
Data Index: 5405871 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7493. Min Act: -0.1700
Data Index: 1264341 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7493. Min Act: -0.1700
Data Index: 4793504 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7493. Min Act: -0.1700
Data Index: 1056796 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7493. Min Range: -6.7493
Max Act: 5.7181. Min Act: -0.1700
Data Index: 2951326 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19