Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.2195. Min Act: -0.1700
Data Index: 3256140 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.1258. Min Act: -0.1700
Data Index: 3062389 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0945. Min Act: -0.1700
Data Index: 1584852 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0945. Min Act: -0.1700
Data Index: 541478 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0633. Min Act: -0.1700
Data Index: 4338458 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0633. Min Act: -0.1700
Data Index: 7559543 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0633. Min Act: -0.1700
Data Index: 5416557 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0320. Min Act: -0.1700
Data Index: 5205421 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0008. Min Act: -0.1700
Data Index: 6975078 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0008. Min Act: -0.1700
Data Index: 4054144 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0320. Min Act: -0.1700
Data Index: 708986 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0008. Min Act: -0.1700
Data Index: 8113594 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9695. Min Act: -0.1700
Data Index: 7949568 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9695. Min Act: -0.1700
Data Index: 6712380 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9383. Min Act: -0.1700
Data Index: 5340435 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2195. Min Range: -7.2195
Max Act: 7.0008. Min Act: -0.1700
Data Index: 7806952 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9383. Min Act: -0.1700
Data Index: 2413157 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9383. Min Act: -0.1700
Data Index: 2012784 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9383. Min Act: -0.1700
Data Index: 7284895 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2195. Min Range: -7.2195
Max Act: 6.9383. Min Act: -0.1700
Data Index: 2343403 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19