Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.9138. Min Act: -0.1700
Data Index: 4626469 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.5076. Min Act: -0.1700
Data Index: 642002 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.4763. Min Act: -0.1700
Data Index: 6405874 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3201. Min Act: -0.1700
Data Index: 4680568 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3513. Min Act: -0.1700
Data Index: 7887221 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.3201. Min Act: -0.1700
Data Index: 5803172 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.2576. Min Act: -0.1700
Data Index: 2175192 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.2576. Min Act: -0.1700
Data Index: 1199137 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.2263. Min Act: -0.1700
Data Index: 8512253 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.2263. Min Act: -0.1700
Data Index: 3252462 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.2263. Min Act: -0.1700
Data Index: 7836132 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.2263. Min Act: -0.1700
Data Index: 7928220 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.1638. Min Act: -0.1700
Data Index: 4363986 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.1013. Min Act: -0.1700
Data Index: 6083824 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.1013. Min Act: -0.1700
Data Index: 1293540 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.0701. Min Act: -0.1700
Data Index: 2564855 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.0701. Min Act: -0.1700
Data Index: 7417745 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.0388. Min Act: -0.1700
Data Index: 1016180 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.0076. Min Act: -0.1700
Data Index: 3011044 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9138. Min Range: -6.9138
Max Act: 6.0388. Min Act: -0.1700
Data Index: 6998296 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19