Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3377 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.4003. Min Act: -0.1700
Data Index: 6928712 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.4003. Min Act: -0.1700
Data Index: 6928715 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.3690. Min Act: -0.1700
Data Index: 6578585 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.3690. Min Act: -0.1700
Data Index: 3481338 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.3065. Min Act: -0.1700
Data Index: 1823605 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.2128. Min Act: -0.1700
Data Index: 7843663 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.2440. Min Act: -0.1700
Data Index: 7166447 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.1815. Min Act: -0.1700
Data Index: 3855544 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.1503. Min Act: -0.1700
Data Index: 6600332 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.1503. Min Act: -0.1700
Data Index: 3706070 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.1190. Min Act: -0.1700
Data Index: 3706078 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0878. Min Act: -0.1700
Data Index: 3706068 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0878. Min Act: -0.1700
Data Index: 5808476 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0878. Min Act: -0.1700
Data Index: 7843660 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0878. Min Act: -0.1700
Data Index: 1086458 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0878. Min Act: -0.1700
Data Index: 7518993 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0878. Min Act: -0.1700
Data Index: 3889673 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0565. Min Act: -0.1700
Data Index: 3706071 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0565. Min Act: -0.1700
Data Index: 2757097 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4003. Min Range: -5.4003
Max Act: 5.0565. Min Act: -0.1700
Data Index: 2365969 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19