Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 824 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0060. Min Range: -5.0060
Max Act: 5.0060. Min Act: -0.1700
Data Index: 6074273 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.9435. Min Act: -0.1700
Data Index: 2173235 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.9435. Min Act: -0.1700
Data Index: 2621961 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.9435. Min Act: -0.1700
Data Index: 6314365 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.8185. Min Act: -0.1700
Data Index: 7024972 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7872. Min Act: -0.1700
Data Index: 8131345 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 4300817 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7560. Min Act: -0.1700
Data Index: 3128208 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3050377 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 4741635 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 7024971 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 7328958 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 3185870 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.7247. Min Act: -0.1700
Data Index: 564984 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.6935. Min Act: -0.1700
Data Index: 6807125 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.6935. Min Act: -0.1700
Data Index: 6179069 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.6935. Min Act: -0.1700
Data Index: 1912764 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.6622. Min Act: -0.1700
Data Index: 8397096 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.6935. Min Act: -0.1700
Data Index: 3091721 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0060. Min Range: -5.0060
Max Act: 4.6935. Min Act: -0.1700
Data Index: 7478147 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #19