Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5142 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.8024. Min Act: -0.1700
Data Index: 6305228 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.6149. Min Act: -0.1700
Data Index: 5802204 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.5524. Min Act: -0.1700
Data Index: 4133130 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.5836. Min Act: -0.1700
Data Index: 1094365 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.5211. Min Act: -0.1700
Data Index: 1673032 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.4586. Min Act: -0.1700
Data Index: 5005045 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3649. Min Act: -0.1700
Data Index: 6494443 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3649. Min Act: -0.1700
Data Index: 2619354 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3649. Min Act: -0.1700
Data Index: 7733569 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3649. Min Act: -0.1700
Data Index: 390334 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3024. Min Act: -0.1700
Data Index: 4538919 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3024. Min Act: -0.1700
Data Index: 1547921 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3024. Min Act: -0.1700
Data Index: 526086 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.3024. Min Act: -0.1700
Data Index: 5323395 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.2711. Min Act: -0.1700
Data Index: 3767701 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.2711. Min Act: -0.1700
Data Index: 3213869 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.2711. Min Act: -0.1700
Data Index: 710971 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.2711. Min Act: -0.1700
Data Index: 5625755 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.2711. Min Act: -0.1700
Data Index: 8372270 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8024. Min Range: -5.8024
Max Act: 5.2711. Min Act: -0.1700
Data Index: 5935177 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19