Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3997 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7399. Min Range: -7.7399
Max Act: 7.7399. Min Act: -0.1700
Data Index: 2363837 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7399. Min Range: -7.7399
Max Act: 7.2711. Min Act: -0.1700
Data Index: 531568 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7399. Min Range: -7.7399
Max Act: 7.2086. Min Act: -0.1700
Data Index: 2650866 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7399. Min Range: -7.7399
Max Act: 7.1461. Min Act: -0.1700
Data Index: 1640447 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7399. Min Range: -7.7399
Max Act: 7.0211. Min Act: -0.1700
Data Index: 8743531 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.9586. Min Act: -0.1700
Data Index: 6164373 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.9586. Min Act: -0.1700
Data Index: 4184519 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.9274. Min Act: -0.1700
Data Index: 5835132 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8961. Min Act: -0.1700
Data Index: 6099384 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8336. Min Act: -0.1700
Data Index: 5279756 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8649. Min Act: -0.1700
Data Index: 4923908 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8961. Min Act: -0.1700
Data Index: 6783851 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8336. Min Act: -0.1700
Data Index: 7821680 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8336. Min Act: -0.1700
Data Index: 950943 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8024. Min Act: -0.1700
Data Index: 3914472 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8649. Min Act: -0.1700
Data Index: 3882484 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8024. Min Act: -0.1700
Data Index: 8181483 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.7711. Min Act: -0.1700
Data Index: 1761600 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.8024. Min Act: -0.1700
Data Index: 3745155 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7399. Min Range: -7.7399
Max Act: 6.7711. Min Act: -0.1700
Data Index: 3718796 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19