Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0109. Min Range: -5.0109
Max Act: 5.0109. Min Act: -0.1700
Data Index: 8256637 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9796. Min Act: -0.1700
Data Index: 8115861 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9796. Min Act: -0.1700
Data Index: 7700511 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9484. Min Act: -0.1700
Data Index: 4787407 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9484. Min Act: -0.1700
Data Index: 2800031 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9171. Min Act: -0.1700
Data Index: 4389883 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8859. Min Act: -0.1700
Data Index: 4591339 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.9171. Min Act: -0.1700
Data Index: 8671441 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8859. Min Act: -0.1700
Data Index: 4685088 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8546. Min Act: -0.1700
Data Index: 6060764 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 7414128 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 1329504 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.8234. Min Act: -0.1700
Data Index: 4956633 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7921. Min Act: -0.1700
Data Index: 4737990 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7609. Min Act: -0.1700
Data Index: 6202550 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7609. Min Act: -0.1700
Data Index: 3818993 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7609. Min Act: -0.1700
Data Index: 7787174 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.7609. Min Act: -0.1700
Data Index: 3241156 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 5748352 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0109. Min Range: -5.0109
Max Act: 4.6984. Min Act: -0.1700
Data Index: 5267968 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19