Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.1995. Min Act: -0.1700
Data Index: 3414868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.1829. Min Act: -0.1700
Data Index: 676974 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.1329. Min Act: -0.1700
Data Index: 6391540 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0827. Min Act: -0.1700
Data Index: 7189016 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0995. Min Act: -0.1700
Data Index: 7669953 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0827. Min Act: -0.1700
Data Index: 5722941 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0154. Min Act: -0.1700
Data Index: 3384073 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0154. Min Act: -0.1700
Data Index: 2890164 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0154. Min Act: -0.1700
Data Index: 8593035 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1995. Min Range: -2.1995
Max Act: 2.0154. Min Act: -0.1700
Data Index: 3203263 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9816. Min Act: -0.1700
Data Index: 6634405 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9986. Min Act: -0.1700
Data Index: 6230373 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9986. Min Act: -0.1700
Data Index: 3811324 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9647. Min Act: -0.1700
Data Index: 7715230 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9816. Min Act: -0.1700
Data Index: 4400440 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9647. Min Act: -0.1700
Data Index: 7091929 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9647. Min Act: -0.1700
Data Index: 3272040 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9477. Min Act: -0.1700
Data Index: 1674969 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9647. Min Act: -0.1700
Data Index: 2365201 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1995. Min Range: -2.1995
Max Act: 1.9477. Min Act: -0.1700
Data Index: 7144859 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19