Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.5153. Min Act: -0.1700
Data Index: 8279408 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.4215. Min Act: -0.1700
Data Index: 3768942 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.2965. Min Act: -0.1700
Data Index: 3278566 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.2653. Min Act: -0.1700
Data Index: 3453555 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.2028. Min Act: -0.1700
Data Index: 3031589 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1715. Min Act: -0.1700
Data Index: 7340752 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.2028. Min Act: -0.1700
Data Index: 211807 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1715. Min Act: -0.1700
Data Index: 8211515 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1403. Min Act: -0.1700
Data Index: 3117803 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.1090. Min Act: -0.1700
Data Index: 1335347 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0778. Min Act: -0.1700
Data Index: 6388355 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0778. Min Act: -0.1700
Data Index: 3873025 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0465. Min Act: -0.1700
Data Index: 6475292 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 568081 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0465. Min Act: -0.1700
Data Index: 3446292 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 8725671 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5153. Min Range: -6.5153
Max Act: 5.9840. Min Act: -0.1700
Data Index: 6751668 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5153. Min Range: -6.5153
Max Act: 6.0153. Min Act: -0.1700
Data Index: 7342597 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5153. Min Range: -6.5153
Max Act: 5.9840. Min Act: -0.1700
Data Index: 8040002 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5153. Min Range: -6.5153
Max Act: 5.9528. Min Act: -0.1700
Data Index: 7902116 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19