Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6030 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.4706. Min Act: -0.1700
Data Index: 268801 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.2206. Min Act: -0.1700
Data Index: 3744743 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.2206. Min Act: -0.1700
Data Index: 5590754 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.1268. Min Act: -0.1700
Data Index: 3854669 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.0956. Min Act: -0.1700
Data Index: 7783031 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.0331. Min Act: -0.1700
Data Index: 5540356 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4706. Min Range: -7.4706
Max Act: 7.0018. Min Act: -0.1700
Data Index: 5291518 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.9706. Min Act: -0.1700
Data Index: 3905058 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.9706. Min Act: -0.1700
Data Index: 4077071 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.9393. Min Act: -0.1700
Data Index: 4979083 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.9393. Min Act: -0.1700
Data Index: 8670106 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.9081. Min Act: -0.1700
Data Index: 8320465 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8768. Min Act: -0.1700
Data Index: 5383066 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8768. Min Act: -0.1700
Data Index: 7598849 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.9081. Min Act: -0.1700
Data Index: 8454391 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8768. Min Act: -0.1700
Data Index: 4782038 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8456. Min Act: -0.1700
Data Index: 1898901 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8768. Min Act: -0.1700
Data Index: 4007651 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8143. Min Act: -0.1700
Data Index: 7263241 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4706. Min Range: -7.4706
Max Act: 6.8143. Min Act: -0.1700
Data Index: 7218390 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19