Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0500. Min Range: -2.0500
Max Act: 2.0500. Min Act: -0.1700
Data Index: 8760153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0500. Min Range: -2.0500
Max Act: 2.0163. Min Act: -0.1700
Data Index: 6361667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9486. Min Act: -0.1700
Data Index: 4416450 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9655. Min Act: -0.1700
Data Index: 2039239 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9486. Min Act: -0.1700
Data Index: 4139190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9486. Min Act: -0.1700
Data Index: 5417235 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9486. Min Act: -0.1700
Data Index: 7601253 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9316. Min Act: -0.1700
Data Index: 2814093 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9316. Min Act: -0.1700
Data Index: 315052 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9316. Min Act: -0.1700
Data Index: 4124713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.8975. Min Act: -0.1700
Data Index: 8450016 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9146. Min Act: -0.1700
Data Index: 6792229 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9146. Min Act: -0.1700
Data Index: 7742204 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9146. Min Act: -0.1700
Data Index: 7804548 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.9146. Min Act: -0.1700
Data Index: 7610299 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.8975. Min Act: -0.1700
Data Index: 3438265 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.8975. Min Act: -0.1700
Data Index: 2754785 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.8975. Min Act: -0.1700
Data Index: 7690478 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.8804. Min Act: -0.1700
Data Index: 7946988 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0500. Min Range: -2.0500
Max Act: 1.8804. Min Act: -0.1700
Data Index: 433076 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19