Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3483 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.7024. Min Act: -0.1700
Data Index: 7594262 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.3899. Min Act: -0.1700
Data Index: 489774 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.2024. Min Act: -0.1700
Data Index: 4007245 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.0774. Min Act: -0.1700
Data Index: 4157631 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7024. Min Range: -7.7024
Max Act: 7.0774. Min Act: -0.1700
Data Index: 5875455 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9837. Min Act: -0.1700
Data Index: 2735464 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9524. Min Act: -0.1700
Data Index: 617483 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9212. Min Act: -0.1700
Data Index: 8680260 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9212. Min Act: -0.1700
Data Index: 363461 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9212. Min Act: -0.1700
Data Index: 5472667 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8899. Min Act: -0.1700
Data Index: 3836872 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.9212. Min Act: -0.1700
Data Index: 5780622 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8899. Min Act: -0.1700
Data Index: 5976790 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8899. Min Act: -0.1700
Data Index: 6117992 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8587. Min Act: -0.1700
Data Index: 8553207 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8587. Min Act: -0.1700
Data Index: 3559476 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.8899. Min Act: -0.1700
Data Index: 224897 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7962. Min Act: -0.1700
Data Index: 8549783 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7962. Min Act: -0.1700
Data Index: 6313382 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7024. Min Range: -7.7024
Max Act: 6.7962. Min Act: -0.1700
Data Index: 4925552 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19