Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 600 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.6388. Min Act: -0.1700
Data Index: 5005313 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.4825. Min Act: -0.1700
Data Index: 6113582 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.4200. Min Act: -0.1700
Data Index: 858358 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.3263. Min Act: -0.1700
Data Index: 4119199 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.2950. Min Act: -0.1700
Data Index: 7761062 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.1700. Min Act: -0.1700
Data Index: 1404654 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.2013. Min Act: -0.1700
Data Index: 6187467 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.1388. Min Act: -0.1700
Data Index: 8612141 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.1388. Min Act: -0.1700
Data Index: 4119188 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.1388. Min Act: -0.1700
Data Index: 2769200 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.1075. Min Act: -0.1700
Data Index: 3040153 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.1075. Min Act: -0.1700
Data Index: 1204092 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0763. Min Act: -0.1700
Data Index: 1720896 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0450. Min Act: -0.1700
Data Index: 5115882 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0138. Min Act: -0.1700
Data Index: 4087398 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0450. Min Act: -0.1700
Data Index: 3976803 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6388. Min Range: -6.6388
Max Act: 5.9825. Min Act: -0.1700
Data Index: 5492385 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0138. Min Act: -0.1700
Data Index: 2906292 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0138. Min Act: -0.1700
Data Index: 5315869 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6388. Min Range: -6.6388
Max Act: 6.0138. Min Act: -0.1700
Data Index: 2076298 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19