Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.3987. Min Act: -0.1700
Data Index: 4067030 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.3987. Min Act: -0.1700
Data Index: 597140 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.3675. Min Act: -0.1700
Data Index: 589048 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.2112. Min Act: -0.1700
Data Index: 7832738 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3987. Min Range: -7.3987
Max Act: 7.0550. Min Act: -0.1700
Data Index: 4514926 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9925. Min Act: -0.1700
Data Index: 7535019 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9612. Min Act: -0.1700
Data Index: 5827643 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.9300. Min Act: -0.1700
Data Index: 4307795 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 7576832 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 7185457 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8987. Min Act: -0.1700
Data Index: 4595818 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8362. Min Act: -0.1700
Data Index: 3002748 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8050. Min Act: -0.1700
Data Index: 2468328 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8362. Min Act: -0.1700
Data Index: 7786414 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8050. Min Act: -0.1700
Data Index: 2972461 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8050. Min Act: -0.1700
Data Index: 2656455 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.8050. Min Act: -0.1700
Data Index: 8142609 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.7425. Min Act: -0.1700
Data Index: 2622557 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.7425. Min Act: -0.1700
Data Index: 6395034 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3987. Min Range: -7.3987
Max Act: 6.7112. Min Act: -0.1700
Data Index: 5777424 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19