Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2169. Min Range: -10.2169
Max Act: 10.2169. Min Act: -0.1700
Data Index: 6352037 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.9669. Min Act: -0.1700
Data Index: 1798835 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.8419. Min Act: -0.1700
Data Index: 7639499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.8419. Min Act: -0.1700
Data Index: 33683 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.8419. Min Act: -0.1700
Data Index: 5711946 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.7794. Min Act: -0.1700
Data Index: 5375839 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.7794. Min Act: -0.1700
Data Index: 8118489 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.7169. Min Act: -0.1700
Data Index: 3328750 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.7169. Min Act: -0.1700
Data Index: 8315166 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.6544. Min Act: -0.1700
Data Index: 1947785 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.6544. Min Act: -0.1700
Data Index: 4935440 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.6544. Min Act: -0.1700
Data Index: 4002166 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 6119172 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 624133 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 6248336 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5919. Min Act: -0.1700
Data Index: 7490152 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5294. Min Act: -0.1700
Data Index: 584983 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5294. Min Act: -0.1700
Data Index: 3404991 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5294. Min Act: -0.1700
Data Index: 3703954 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2169. Min Range: -10.2169
Max Act: 9.5294. Min Act: -0.1700
Data Index: 5741303 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19