Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5917 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.2646. Min Act: -0.1700
Data Index: 6011273 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.2333. Min Act: -0.1700
Data Index: 4908597 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0146. Min Act: -0.1700
Data Index: 6323743 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.9208. Min Act: -0.1700
Data Index: 2834157 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8583. Min Act: -0.1700
Data Index: 4779229 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8896. Min Act: -0.1700
Data Index: 5256744 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8583. Min Act: -0.1700
Data Index: 1999873 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8583. Min Act: -0.1700
Data Index: 7309898 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7958. Min Act: -0.1700
Data Index: 3061737 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8271. Min Act: -0.1700
Data Index: 5147370 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8271. Min Act: -0.1700
Data Index: 5891815 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.8271. Min Act: -0.1700
Data Index: 3039991 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7958. Min Act: -0.1700
Data Index: 6761616 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7333. Min Act: -0.1700
Data Index: 8547978 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7646. Min Act: -0.1700
Data Index: 8499781 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7646. Min Act: -0.1700
Data Index: 7047321 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7958. Min Act: -0.1700
Data Index: 7268488 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7333. Min Act: -0.1700
Data Index: 932904 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7333. Min Act: -0.1700
Data Index: 4245046 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2646. Min Range: -6.2646
Max Act: 5.7021. Min Act: -0.1700
Data Index: 395998 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19