Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.4797. Min Act: -0.1700
Data Index: 4029026 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.3547. Min Act: -0.1700
Data Index: 7995033 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.2922. Min Act: -0.1700
Data Index: 1336226 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.2297. Min Act: -0.1700
Data Index: 3557548 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.2922. Min Act: -0.1700
Data Index: 315499 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.2297. Min Act: -0.1700
Data Index: 7747546 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.1672. Min Act: -0.1700
Data Index: 2717982 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.1672. Min Act: -0.1700
Data Index: 2942678 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.1672. Min Act: -0.1700
Data Index: 3445441 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.1672. Min Act: -0.1700
Data Index: 3445445 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.0110. Min Act: -0.1700
Data Index: 5043026 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4797. Min Range: -8.4797
Max Act: 8.0110. Min Act: -0.1700
Data Index: 342438 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 1919751 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.9485. Min Act: -0.1700
Data Index: 7546748 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 5154113 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.9485. Min Act: -0.1700
Data Index: 1414773 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.9172. Min Act: -0.1700
Data Index: 342439 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 4811714 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.8547. Min Act: -0.1699
Data Index: 3825805 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4797. Min Range: -8.4797
Max Act: 7.8547. Min Act: -0.1700
Data Index: 1199287 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19