Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2719 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0488. Min Range: -5.0488
Max Act: 5.0488. Min Act: -0.1700
Data Index: 2570751 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.9551. Min Act: -0.1700
Data Index: 2146468 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.9238. Min Act: -0.1700
Data Index: 4272028 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.8301. Min Act: -0.1700
Data Index: 5841565 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.8301. Min Act: -0.1700
Data Index: 8805471 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7988. Min Act: -0.1700
Data Index: 7157419 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7988. Min Act: -0.1700
Data Index: 3055219 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7363. Min Act: -0.1700
Data Index: 7978603 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7363. Min Act: -0.1700
Data Index: 4864010 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7051. Min Act: -0.1700
Data Index: 2231510 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7051. Min Act: -0.1699
Data Index: 8700400 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7051. Min Act: -0.1700
Data Index: 3545865 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.7051. Min Act: -0.1700
Data Index: 6367634 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.6426. Min Act: -0.1700
Data Index: 5586861 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.6426. Min Act: -0.1700
Data Index: 369057 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.6113. Min Act: -0.1700
Data Index: 8459952 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.6113. Min Act: -0.1700
Data Index: 3098080 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.6113. Min Act: -0.1700
Data Index: 3618976 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.5801. Min Act: -0.1700
Data Index: 341327 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0488. Min Range: -5.0488
Max Act: 4.5801. Min Act: -0.1700
Data Index: 1456516 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19