Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.3530. Min Act: -0.1700
Data Index: 548635 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.3530. Min Act: -0.1700
Data Index: 7831264 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0717. Min Act: -0.1700
Data Index: 7720648 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1030. Min Act: -0.1700
Data Index: 1673065 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1030. Min Act: -0.1700
Data Index: 8685133 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1030. Min Act: -0.1700
Data Index: 8556507 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1030. Min Act: -0.1700
Data Index: 4354023 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1030. Min Act: -0.1700
Data Index: 3676116 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0717. Min Act: -0.1700
Data Index: 5013198 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0717. Min Act: -0.1700
Data Index: 2383372 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0717. Min Act: -0.1700
Data Index: 2437669 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0405. Min Act: -0.1700
Data Index: 6144500 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0092. Min Act: -0.1700
Data Index: 7098389 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3530. Min Range: -4.3530
Max Act: 3.9780. Min Act: -0.1700
Data Index: 8502225 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.0092. Min Act: -0.1700
Data Index: 3841363 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3530. Min Range: -4.3530
Max Act: 3.9780. Min Act: -0.1700
Data Index: 5160316 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3530. Min Range: -4.3530
Max Act: 3.9780. Min Act: -0.1700
Data Index: 4977196 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3530. Min Range: -4.3530
Max Act: 3.9780. Min Act: -0.1700
Data Index: 513503 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3530. Min Range: -4.3530
Max Act: 3.9780. Min Act: -0.1700
Data Index: 7577093 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3530. Min Range: -4.3530
Max Act: 3.9780. Min Act: -0.1700
Data Index: 5973588 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19