Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1229 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.4616. Min Act: -0.1700
Data Index: 4978938 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.3637. Min Act: -0.1700
Data Index: 4570348 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.3310. Min Act: -0.1700
Data Index: 469235 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.2486. Min Act: -0.1700
Data Index: 8587707 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.2321. Min Act: -0.1700
Data Index: 6444276 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.2155. Min Act: -0.1700
Data Index: 5184731 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1824. Min Act: -0.1700
Data Index: 1760323 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1990. Min Act: -0.1700
Data Index: 7115922 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1990. Min Act: -0.1700
Data Index: 6386532 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1824. Min Act: -0.1700
Data Index: 1685423 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1824. Min Act: -0.1700
Data Index: 6462180 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1824. Min Act: -0.1700
Data Index: 4164410 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1657. Min Act: -0.1700
Data Index: 5360547 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1491. Min Act: -0.1700
Data Index: 1457146 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1491. Min Act: -0.1700
Data Index: 4929572 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1157. Min Act: -0.1700
Data Index: 525840 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1324. Min Act: -0.1700
Data Index: 7511975 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1324. Min Act: -0.1700
Data Index: 4134751 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1324. Min Act: -0.1700
Data Index: 4917098 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4616. Min Range: -2.4616
Max Act: 2.1157. Min Act: -0.1700
Data Index: 7623679 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19