Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4770 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.9247. Min Act: -0.1700
Data Index: 2636521 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.7372. Min Act: -0.1700
Data Index: 895401 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.5809. Min Act: -0.1700
Data Index: 6626650 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.4872. Min Act: -0.1700
Data Index: 2140775 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.4872. Min Act: -0.1700
Data Index: 5389298 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.4247. Min Act: -0.1700
Data Index: 8297165 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.4247. Min Act: -0.1700
Data Index: 3822797 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.3934. Min Act: -0.1700
Data Index: 1952382 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.4247. Min Act: -0.1700
Data Index: 5848892 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.3309. Min Act: -0.1700
Data Index: 8330266 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2997. Min Act: -0.1700
Data Index: 4160567 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.3309. Min Act: -0.1700
Data Index: 8144395 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2997. Min Act: -0.1700
Data Index: 5521374 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2684. Min Act: -0.1700
Data Index: 1164309 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2684. Min Act: -0.1700
Data Index: 5426671 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2372. Min Act: -0.1700
Data Index: 3132863 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2372. Min Act: -0.1700
Data Index: 7467436 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2372. Min Act: -0.1700
Data Index: 169813 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2372. Min Act: -0.1700
Data Index: 8812912 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9247. Min Range: -7.9247
Max Act: 7.2372. Min Act: -0.1700
Data Index: 4674911 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19