Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.2703. Min Act: -0.1696
Data Index: 2711074 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.2391. Min Act: -0.1700
Data Index: 8438050 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.2703. Min Act: -0.1700
Data Index: 4625411 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.2078. Min Act: -0.1700
Data Index: 6652783 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.1141. Min Act: -0.1700
Data Index: 8019553 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2703. Min Range: -6.2703
Max Act: 6.1141. Min Act: -0.1700
Data Index: 1617976 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9891. Min Act: -0.1700
Data Index: 2419524 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9891. Min Act: -0.1700
Data Index: 4849432 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9891. Min Act: -0.1700
Data Index: 6137298 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9578. Min Act: -0.1700
Data Index: 4849430 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9266. Min Act: -0.1700
Data Index: 4625407 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9266. Min Act: -0.1700
Data Index: 5706087 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9266. Min Act: -0.1700
Data Index: 7515411 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.9266. Min Act: -0.1700
Data Index: 2816875 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.8953. Min Act: -0.1700
Data Index: 8019552 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.8641. Min Act: -0.1700
Data Index: 435476 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.8328. Min Act: -0.1700
Data Index: 3563580 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.8328. Min Act: -0.1700
Data Index: 4276354 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.8641. Min Act: -0.1700
Data Index: 8436842 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2703. Min Range: -6.2703
Max Act: 5.8641. Min Act: -0.1700
Data Index: 7069266 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19