Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1575 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2671. Min Range: -5.2671
Max Act: 5.2671. Min Act: -0.1700
Data Index: 6635406 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2671. Min Range: -5.2671
Max Act: 5.0484. Min Act: -0.1700
Data Index: 782376 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2671. Min Range: -5.2671
Max Act: 5.0484. Min Act: -0.1700
Data Index: 2261755 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.9546. Min Act: -0.1700
Data Index: 6031840 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.9546. Min Act: -0.1700
Data Index: 5138498 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.9859. Min Act: -0.1700
Data Index: 4137805 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.9234. Min Act: -0.1700
Data Index: 5071726 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.9234. Min Act: -0.1700
Data Index: 2285660 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8921. Min Act: -0.1700
Data Index: 2890004 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8921. Min Act: -0.1700
Data Index: 2833712 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8609. Min Act: -0.1700
Data Index: 8236025 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8609. Min Act: -0.1700
Data Index: 3238156 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8921. Min Act: -0.1700
Data Index: 2214019 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8609. Min Act: -0.1700
Data Index: 407647 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8921. Min Act: -0.1700
Data Index: 362717 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8609. Min Act: -0.1700
Data Index: 4901414 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.7984. Min Act: -0.1700
Data Index: 678864 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8296. Min Act: -0.1700
Data Index: 5493263 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8296. Min Act: -0.1700
Data Index: 733810 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2671. Min Range: -5.2671
Max Act: 4.8609. Min Act: -0.1700
Data Index: 1702301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19