Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.3118. Min Act: -0.1700
Data Index: 3594950 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.2493. Min Act: -0.1700
Data Index: 3433085 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.2180. Min Act: -0.1700
Data Index: 2577085 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.1555. Min Act: -0.1700
Data Index: 2103035 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.1243. Min Act: -0.1700
Data Index: 6715259 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.1555. Min Act: -0.1700
Data Index: 1461914 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0618. Min Act: -0.1700
Data Index: 694887 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0618. Min Act: -0.1700
Data Index: 2550683 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0930. Min Act: -0.1700
Data Index: 3265251 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0618. Min Act: -0.1700
Data Index: 6061305 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0305. Min Act: -0.1700
Data Index: 3934467 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0305. Min Act: -0.1700
Data Index: 6504398 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3118. Min Range: -4.3118
Max Act: 4.0305. Min Act: -0.1700
Data Index: 4014433 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9680. Min Act: -0.1700
Data Index: 650525 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9992. Min Act: -0.1700
Data Index: 5265235 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9992. Min Act: -0.1700
Data Index: 8680599 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9680. Min Act: -0.1700
Data Index: 1580497 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9680. Min Act: -0.1700
Data Index: 1329609 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9992. Min Act: -0.1700
Data Index: 7514880 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3118. Min Range: -4.3118
Max Act: 3.9680. Min Act: -0.1700
Data Index: 342551 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19