Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3731 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3225. Min Range: -7.3225
Max Act: 7.3225. Min Act: -0.1700
Data Index: 6760197 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.9163. Min Act: -0.1700
Data Index: 6512149 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8850. Min Act: -0.1700
Data Index: 6512050 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3310647 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3517211 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8850. Min Act: -0.1700
Data Index: 4854082 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8538. Min Act: -0.1700
Data Index: 7837472 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8538. Min Act: -0.1700
Data Index: 8785929 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.8225. Min Act: -0.1700
Data Index: 3384875 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7913. Min Act: -0.1700
Data Index: 2033631 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7913. Min Act: -0.1700
Data Index: 5540076 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7913. Min Act: -0.1700
Data Index: 6831397 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7600. Min Act: -0.1700
Data Index: 1232452 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7600. Min Act: -0.1700
Data Index: 7054821 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7600. Min Act: -0.1700
Data Index: 5911254 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7600. Min Act: -0.1700
Data Index: 3699130 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7288. Min Act: -0.1700
Data Index: 208304 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7288. Min Act: -0.1700
Data Index: 488955 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.7600. Min Act: -0.1700
Data Index: 6660195 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3225. Min Range: -7.3225
Max Act: 6.6975. Min Act: -0.1700
Data Index: 129860 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19