Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.6916. Min Act: -0.1700
Data Index: 3170963 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.4729. Min Act: -0.1700
Data Index: 6173055 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.2854. Min Act: -0.1700
Data Index: 768239 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.2854. Min Act: -0.1700
Data Index: 3366263 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.2854. Min Act: -0.1700
Data Index: 8395905 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.2854. Min Act: -0.1700
Data Index: 7224304 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.2541. Min Act: -0.1700
Data Index: 1427551 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.2229. Min Act: -0.1700
Data Index: 2880542 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.1604. Min Act: -0.1700
Data Index: 3155416 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.1916. Min Act: -0.1700
Data Index: 7724200 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.1604. Min Act: -0.1700
Data Index: 401933 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.1604. Min Act: -0.1700
Data Index: 2885636 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0979. Min Act: -0.1700
Data Index: 3521903 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0979. Min Act: -0.1700
Data Index: 8645856 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0979. Min Act: -0.1700
Data Index: 5289750 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0979. Min Act: -0.1700
Data Index: 8669634 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0979. Min Act: -0.1700
Data Index: 5645026 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0979. Min Act: -0.1700
Data Index: 561511 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0666. Min Act: -0.1700
Data Index: 5704679 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6916. Min Range: -5.6916
Max Act: 5.0666. Min Act: -0.1700
Data Index: 3619316 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19