Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5811 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0818. Min Range: -8.0818
Max Act: 8.0818. Min Act: -0.1700
Data Index: 4800867 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.9568. Min Act: -0.1700
Data Index: 6470216 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.9568. Min Act: -0.1700
Data Index: 2017253 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.8943. Min Act: -0.1700
Data Index: 2002017 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.8943. Min Act: -0.1700
Data Index: 99559 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.8943. Min Act: -0.1700
Data Index: 48071 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.8631. Min Act: -0.1700
Data Index: 8512065 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.8943. Min Act: -0.1700
Data Index: 3470434 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.8006. Min Act: -0.1700
Data Index: 7152097 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.7381. Min Act: -0.1700
Data Index: 853047 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.7068. Min Act: -0.1700
Data Index: 3026464 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.6756. Min Act: -0.1700
Data Index: 829795 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.6443. Min Act: -0.1700
Data Index: 4167114 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.6443. Min Act: -0.1700
Data Index: 6777915 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.6443. Min Act: -0.1700
Data Index: 5710079 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.6131. Min Act: -0.1700
Data Index: 5494831 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.5506. Min Act: -0.1700
Data Index: 2844492 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.5818. Min Act: -0.1700
Data Index: 5023333 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.5818. Min Act: -0.1700
Data Index: 4210020 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0818. Min Range: -8.0818
Max Act: 7.5193. Min Act: -0.1700
Data Index: 107266 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19