Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.3911. Min Act: -0.1700
Data Index: 3947931 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.2661. Min Act: -0.1700
Data Index: 6950883 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.2036. Min Act: -0.1700
Data Index: 265473 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.1411. Min Act: -0.1700
Data Index: 7331225 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.0786. Min Act: -0.1700
Data Index: 3314727 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.0786. Min Act: -0.1700
Data Index: 4911016 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3911. Min Range: -8.3911
Max Act: 8.0161. Min Act: -0.1700
Data Index: 463477 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.9536. Min Act: -0.1700
Data Index: 4763881 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.8911. Min Act: -0.1700
Data Index: 6527206 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.8911. Min Act: -0.1700
Data Index: 2947519 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.8911. Min Act: -0.1700
Data Index: 1179041 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.8911. Min Act: -0.1700
Data Index: 3947930 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.8911. Min Act: -0.1700
Data Index: 7616975 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.7973. Min Act: -0.1700
Data Index: 2906378 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.8286. Min Act: -0.1700
Data Index: 2668863 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.7661. Min Act: -0.1700
Data Index: 5928914 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.7661. Min Act: -0.1700
Data Index: 4919928 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.7348. Min Act: -0.1700
Data Index: 2426314 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.7348. Min Act: -0.1700
Data Index: 2861397 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3911. Min Range: -8.3911
Max Act: 7.7036. Min Act: -0.1700
Data Index: 102047 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19