Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4863 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.5010. Min Act: -0.1700
Data Index: 8034176 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0635. Min Act: -0.1700
Data Index: 518132 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5010. Min Range: -7.5010
Max Act: 7.0323. Min Act: -0.1700
Data Index: 2534107 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9698. Min Act: -0.1700
Data Index: 5794467 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 7677279 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.9385. Min Act: -0.1700
Data Index: 4662917 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.8448. Min Act: -0.1700
Data Index: 3142677 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.7510. Min Act: -0.1700
Data Index: 7080169 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.7510. Min Act: -0.1700
Data Index: 6045048 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.7198. Min Act: -0.1700
Data Index: 7443361 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.7198. Min Act: -0.1699
Data Index: 6101731 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.7198. Min Act: -0.1700
Data Index: 8616235 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.7198. Min Act: -0.1700
Data Index: 5915675 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.6885. Min Act: -0.1700
Data Index: 3829229 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.6260. Min Act: -0.1700
Data Index: 5866011 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.5948. Min Act: -0.1700
Data Index: 2451313 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.5948. Min Act: -0.1700
Data Index: 6838781 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.5948. Min Act: -0.1700
Data Index: 7199316 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.5948. Min Act: -0.1700
Data Index: 145622 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5010. Min Range: -7.5010
Max Act: 6.5635. Min Act: -0.1700
Data Index: 3158149 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19