Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.6610. Min Act: -0.1700
Data Index: 3342070 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.5672. Min Act: -0.1700
Data Index: 5340413 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.4735. Min Act: -0.1700
Data Index: 1889672 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.3485. Min Act: -0.1700
Data Index: 5340412 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.3172. Min Act: -0.1700
Data Index: 7924574 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2859. Min Act: -0.1700
Data Index: 340776 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2859. Min Act: -0.1700
Data Index: 4933883 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2859. Min Act: -0.1700
Data Index: 116777 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2859. Min Act: -0.1700
Data Index: 3180622 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2547. Min Act: -0.1700
Data Index: 5877106 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2547. Min Act: -0.1700
Data Index: 8050011 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.2234. Min Act: -0.1700
Data Index: 968607 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1922. Min Act: -0.1700
Data Index: 714009 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1922. Min Act: -0.1700
Data Index: 4818458 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1922. Min Act: -0.1700
Data Index: 6560572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1922. Min Act: -0.1700
Data Index: 8194153 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1922. Min Act: -0.1700
Data Index: 2562335 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1922. Min Act: -0.1700
Data Index: 7169818 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1609. Min Act: -0.1700
Data Index: 428859 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6610. Min Range: -4.6610
Max Act: 4.1609. Min Act: -0.1700
Data Index: 1231708 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19