Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4652. Min Range: -9.4652
Max Act: 9.4652. Min Act: -0.1700
Data Index: 8519460 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4652. Min Range: -9.4652
Max Act: 9.0277. Min Act: -0.1700
Data Index: 6417737 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.8402. Min Act: -0.1700
Data Index: 1577806 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.7777. Min Act: -0.1700
Data Index: 2919517 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.7152. Min Act: -0.1700
Data Index: 6323999 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.6527. Min Act: -0.1700
Data Index: 6958634 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.5902. Min Act: -0.1700
Data Index: 8542208 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.5277. Min Act: -0.1700
Data Index: 3834008 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.5902. Min Act: -0.1700
Data Index: 6417736 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.5277. Min Act: -0.1700
Data Index: 6967176 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4652. Min Act: -0.1700
Data Index: 7082074 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.5277. Min Act: -0.1700
Data Index: 8649184 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.5277. Min Act: -0.1700
Data Index: 518259 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4652. Min Act: -0.1700
Data Index: 8777429 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4027. Min Act: -0.1700
Data Index: 2269500 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4652. Min Act: -0.1700
Data Index: 5173908 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4027. Min Act: -0.1700
Data Index: 7836150 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4027. Min Act: -0.1700
Data Index: 5423835 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4652. Min Act: -0.1700
Data Index: 108204 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4652. Min Range: -9.4652
Max Act: 8.4027. Min Act: -0.1700
Data Index: 8669528 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19