Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2338 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.9555. Min Act: -0.1700
Data Index: 361377 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.7680. Min Act: -0.1700
Data Index: 8165916 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.6742. Min Act: -0.1700
Data Index: 117256 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.6430. Min Act: -0.1700
Data Index: 4353721 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.6117. Min Act: -0.1700
Data Index: 1297282 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.6117. Min Act: -0.1700
Data Index: 1296342 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.5805. Min Act: -0.1700
Data Index: 2255083 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.5492. Min Act: -0.1700
Data Index: 7796708 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.5492. Min Act: -0.1700
Data Index: 2169693 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.5180. Min Act: -0.1700
Data Index: 5031763 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4867. Min Act: -0.1700
Data Index: 5975798 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4867. Min Act: -0.1700
Data Index: 2444746 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4555. Min Act: -0.1700
Data Index: 6448346 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4867. Min Act: -0.1700
Data Index: 6103603 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4867. Min Act: -0.1700
Data Index: 7002595 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4555. Min Act: -0.1700
Data Index: 1441819 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4555. Min Act: -0.1700
Data Index: 719510 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4867. Min Act: -0.1700
Data Index: 2114670 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4555. Min Act: -0.1700
Data Index: 5128814 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9555. Min Range: -6.9555
Max Act: 6.4555. Min Act: -0.1700
Data Index: 2013417 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19