Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2624. Min Range: -8.2624
Max Act: 8.2624. Min Act: -0.1700
Data Index: 1339995 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2624. Min Range: -8.2624
Max Act: 8.0749. Min Act: -0.1700
Data Index: 6377647 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2624. Min Range: -8.2624
Max Act: 8.0749. Min Act: -0.1700
Data Index: 6012301 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2624. Min Range: -8.2624
Max Act: 8.0749. Min Act: -0.1700
Data Index: 4481558 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.8874. Min Act: -0.1700
Data Index: 2481871 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7937. Min Act: -0.1700
Data Index: 3993312 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7624. Min Act: -0.1700
Data Index: 3898733 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7624. Min Act: -0.1700
Data Index: 431178 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7624. Min Act: -0.1700
Data Index: 6415252 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7624. Min Act: -0.1700
Data Index: 7093512 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7312. Min Act: -0.1700
Data Index: 3701214 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7312. Min Act: -0.1700
Data Index: 2245015 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7312. Min Act: -0.1700
Data Index: 6721086 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.7312. Min Act: -0.1700
Data Index: 5424573 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.6999. Min Act: -0.1700
Data Index: 2834210 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.6374. Min Act: -0.1700
Data Index: 8577492 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.6374. Min Act: -0.1700
Data Index: 8068910 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.6062. Min Act: -0.1700
Data Index: 614994 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.6062. Min Act: -0.1700
Data Index: 3312654 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2624. Min Range: -8.2624
Max Act: 7.6062. Min Act: -0.1700
Data Index: 5920305 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19