Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0887. Min Range: -8.0887
Max Act: 8.0887. Min Act: -0.1700
Data Index: 1106053 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.8387. Min Act: -0.1700
Data Index: 5465913 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.8387. Min Act: -0.1700
Data Index: 6126079 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.5887. Min Act: -0.1700
Data Index: 4354892 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.5575. Min Act: -0.1700
Data Index: 1154507 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.5262. Min Act: -0.1700
Data Index: 7536516 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4950. Min Act: -0.1700
Data Index: 4606777 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4637. Min Act: -0.1700
Data Index: 7208040 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4325. Min Act: -0.1700
Data Index: 6173403 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4325. Min Act: -0.1700
Data Index: 7200132 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4012. Min Act: -0.1700
Data Index: 2723330 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4012. Min Act: -0.1700
Data Index: 4601378 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4012. Min Act: -0.1700
Data Index: 586255 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.4012. Min Act: -0.1700
Data Index: 6136996 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.3700. Min Act: -0.1700
Data Index: 517498 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.3700. Min Act: -0.1700
Data Index: 7930128 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.3700. Min Act: -0.1700
Data Index: 8237807 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.3387. Min Act: -0.1700
Data Index: 7542459 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.3387. Min Act: -0.1700
Data Index: 5948538 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0887. Min Range: -8.0887
Max Act: 7.3075. Min Act: -0.1700
Data Index: 7780981 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19