Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3247 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.7661. Min Act: -0.1700
Data Index: 2028913 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.7348. Min Act: -0.1700
Data Index: 527047 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.7036. Min Act: -0.1700
Data Index: 4609872 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.7036. Min Act: -0.1700
Data Index: 3139059 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.6411. Min Act: -0.1700
Data Index: 4266286 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.6411. Min Act: -0.1700
Data Index: 4366420 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.6411. Min Act: -0.1700
Data Index: 3090037 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.6098. Min Act: -0.1700
Data Index: 6569906 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.5473. Min Act: -0.1700
Data Index: 154778 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6194970 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.5473. Min Act: -0.1700
Data Index: 8475810 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.5161. Min Act: -0.1700
Data Index: 2028917 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.4536. Min Act: -0.1700
Data Index: 4266285 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.4223. Min Act: -0.1700
Data Index: 2028914 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.4223. Min Act: -0.1700
Data Index: 3090036 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.4223. Min Act: -0.1700
Data Index: 127079 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.3911. Min Act: -0.1700
Data Index: 5978829 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.3598. Min Act: -0.1700
Data Index: 5722249 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.3598. Min Act: -0.1700
Data Index: 632831 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7661. Min Range: -5.7661
Max Act: 5.3598. Min Act: -0.1700
Data Index: 4524228 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19