Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.5026. Min Act: -0.1700
Data Index: 6544022 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.4401. Min Act: -0.1700
Data Index: 5476673 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.4088. Min Act: -0.1700
Data Index: 7654023 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.3151. Min Act: -0.1700
Data Index: 1652197 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2838. Min Act: -0.1700
Data Index: 1440269 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2838. Min Act: -0.1700
Data Index: 7745623 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2838. Min Act: -0.1700
Data Index: 3373368 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2526. Min Act: -0.1700
Data Index: 7623574 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2213. Min Act: -0.1700
Data Index: 6473618 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.2526. Min Act: -0.1700
Data Index: 7014261 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1588. Min Act: -0.1700
Data Index: 4251729 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1588. Min Act: -0.1700
Data Index: 3729953 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 353484 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 8222046 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 1342801 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.0963. Min Act: -0.1700
Data Index: 2247919 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 7137805 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1588. Min Act: -0.1700
Data Index: 793983 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.0651. Min Act: -0.1700
Data Index: 3536520 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5026. Min Range: -5.5026
Max Act: 5.1276. Min Act: -0.1700
Data Index: 2473709 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19