Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 362 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.5549. Min Act: -0.1700
Data Index: 4742168 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.5549. Min Act: -0.1700
Data Index: 2132617 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.5549. Min Act: -0.1700
Data Index: 8221718 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 3499834 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 366093 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 4978087 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 1119026 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 4658379 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 4581499 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4299. Min Act: -0.1700
Data Index: 3767679 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 788884 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 3514552 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 2470342 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 2371022 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 2351187 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 54680 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 22612 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 1616851 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 1543339 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5549. Min Range: -8.5549
Max Act: 8.4924. Min Act: -0.1700
Data Index: 1452028 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19