Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.6071. Min Act: -0.1700
Data Index: 7183904 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4778. Min Act: -0.1700
Data Index: 4488392 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4941. Min Act: -0.1700
Data Index: 6794903 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4616. Min Act: -0.1700
Data Index: 2807133 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4616. Min Act: -0.1700
Data Index: 4331235 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4616. Min Act: -0.1700
Data Index: 2844152 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4453. Min Act: -0.1700
Data Index: 3860196 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4453. Min Act: -0.1700
Data Index: 3717133 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4291. Min Act: -0.1700
Data Index: 3140261 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4128. Min Act: -0.1700
Data Index: 931811 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4128. Min Act: -0.1700
Data Index: 7009015 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3965. Min Act: -0.1700
Data Index: 1959672 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3965. Min Act: -0.1700
Data Index: 7336214 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.4128. Min Act: -0.1700
Data Index: 5583219 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3801. Min Act: -0.1700
Data Index: 5614617 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3638. Min Act: -0.1700
Data Index: 2780697 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3965. Min Act: -0.1700
Data Index: 4642884 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3638. Min Act: -0.1700
Data Index: 4477264 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3638. Min Act: -0.1700
Data Index: 6981735 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6071. Min Range: -2.6071
Max Act: 2.3474. Min Act: -0.1700
Data Index: 30034 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19