Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3086 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1406. Min Act: -0.1700
Data Index: 2930117 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1406. Min Act: -0.1700
Data Index: 4924197 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1406. Min Act: -0.1700
Data Index: 4951957 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1248. Min Act: -0.1700
Data Index: 6116205 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1406. Min Act: -0.1700
Data Index: 6341707 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1248. Min Act: -0.1700
Data Index: 3910881 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.1091. Min Act: -0.1700
Data Index: 3370813 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0775. Min Act: -0.1700
Data Index: 1070133 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0775. Min Act: -0.1700
Data Index: 6184202 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0933. Min Act: -0.1700
Data Index: 953077 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0460. Min Act: -0.1700
Data Index: 783939 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0618. Min Act: -0.1700
Data Index: 6033844 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0618. Min Act: -0.1700
Data Index: 4082055 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0618. Min Act: -0.1700
Data Index: 5377063 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0460. Min Act: -0.1700
Data Index: 7144064 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0460. Min Act: -0.1700
Data Index: 3377634 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0460. Min Act: -0.1700
Data Index: 3544663 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0302. Min Act: -0.1700
Data Index: 6792934 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0144. Min Act: -0.1700
Data Index: 1551108 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1406. Min Range: -3.1406
Max Act: 3.0144. Min Act: -0.1700
Data Index: 7653185 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19