Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 957 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.6348. Min Act: -0.1700
Data Index: 1725207 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.6661. Min Act: -0.1700
Data Index: 6531489 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.6348. Min Act: -0.1700
Data Index: 5790321 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.6036. Min Act: -0.1700
Data Index: 725313 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.5411. Min Act: -0.1700
Data Index: 2067338 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.4786. Min Act: -0.1700
Data Index: 725316 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.4786. Min Act: -0.1700
Data Index: 282735 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.4473. Min Act: -0.1700
Data Index: 31805 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.4473. Min Act: -0.1700
Data Index: 6081358 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.4161. Min Act: -0.1700
Data Index: 6239960 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.3848. Min Act: -0.1700
Data Index: 6861218 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.3848. Min Act: -0.1700
Data Index: 4292218 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.3536. Min Act: -0.1700
Data Index: 2618317 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.3223. Min Act: -0.1700
Data Index: 8520387 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.3223. Min Act: -0.1700
Data Index: 1202904 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.2911. Min Act: -0.1700
Data Index: 3594393 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.2911. Min Act: -0.1700
Data Index: 265781 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.2598. Min Act: -0.1700
Data Index: 89827 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.2598. Min Act: -0.1700
Data Index: 2274214 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6661. Min Range: -5.6661
Max Act: 5.2286. Min Act: -0.1700
Data Index: 8263271 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19