Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.7214. Min Act: -0.1700
Data Index: 8643871 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6901. Min Act: -0.1700
Data Index: 4958156 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6901. Min Act: -0.1700
Data Index: 2573397 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6588. Min Act: -0.1700
Data Index: 2389689 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6432. Min Act: -0.1700
Data Index: 6280177 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6432. Min Act: -0.1700
Data Index: 7135129 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6432. Min Act: -0.1700
Data Index: 301208 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6432. Min Act: -0.1700
Data Index: 6545738 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 1016126 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6119. Min Act: -0.1700
Data Index: 2239238 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 5111979 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 3079322 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 4249512 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 119738 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6119. Min Act: -0.1700
Data Index: 1089968 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6119. Min Act: -0.1700
Data Index: 5273301 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6119. Min Act: -0.1700
Data Index: 1691354 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 7993583 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.6275. Min Act: -0.1700
Data Index: 5974525 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7214. Min Range: -3.7214
Max Act: 3.5962. Min Act: -0.1700
Data Index: 3327045 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19