Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.6166. Min Act: -0.1700
Data Index: 4836334 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.4604. Min Act: -0.1700
Data Index: 8661204 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.4291. Min Act: -0.1700
Data Index: 2750679 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.4291. Min Act: -0.1700
Data Index: 907756 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.4291. Min Act: -0.1700
Data Index: 8203077 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3666. Min Act: -0.1700
Data Index: 8007200 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3354. Min Act: -0.1700
Data Index: 1800671 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3354. Min Act: -0.1700
Data Index: 6249334 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3354. Min Act: -0.1700
Data Index: 207521 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3354. Min Act: -0.1700
Data Index: 6899050 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3354. Min Act: -0.1700
Data Index: 8801774 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3041. Min Act: -0.1700
Data Index: 8119707 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.3041. Min Act: -0.1700
Data Index: 2809751 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2729. Min Act: -0.1700
Data Index: 2326341 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2729. Min Act: -0.1700
Data Index: 4353676 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2416. Min Act: -0.1700
Data Index: 2152775 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2104. Min Act: -0.1700
Data Index: 5278160 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2104. Min Act: -0.1700
Data Index: 4604656 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2104. Min Act: -0.1700
Data Index: 4353745 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6166. Min Range: -5.6166
Max Act: 5.2104. Min Act: -0.1700
Data Index: 4122253 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19