Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5607 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.3862. Min Act: -0.1700
Data Index: 3639054 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.1362. Min Act: -0.1700
Data Index: 8723730 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0737. Min Act: -0.1700
Data Index: 3770828 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0112. Min Act: -0.1700
Data Index: 1083993 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0737. Min Act: -0.1700
Data Index: 675180 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0112. Min Act: -0.1700
Data Index: 271978 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0112. Min Act: -0.1700
Data Index: 6955616 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0112. Min Act: -0.1700
Data Index: 2995152 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0112. Min Act: -0.1700
Data Index: 2975719 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3862. Min Range: -10.3862
Max Act: 10.0112. Min Act: -0.1700
Data Index: 5294640 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.9487. Min Act: -0.1700
Data Index: 4929353 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1700
Data Index: 5223592 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1700
Data Index: 2170158 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1700
Data Index: 2445700 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1700
Data Index: 6295037 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1700
Data Index: 3587387 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1699
Data Index: 6173631 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8862. Min Act: -0.1700
Data Index: 5749267 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.8237. Min Act: -0.1700
Data Index: 2970280 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3862. Min Range: -10.3862
Max Act: 9.7612. Min Act: -0.1700
Data Index: 3837206 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19