Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4112 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2314. Min Range: -6.2314
Max Act: 6.2314. Min Act: -0.1700
Data Index: 8681843 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2314. Min Range: -6.2314
Max Act: 6.0752. Min Act: -0.1700
Data Index: 5179033 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2314. Min Range: -6.2314
Max Act: 6.0439. Min Act: -0.1700
Data Index: 4304412 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.9814. Min Act: -0.1700
Data Index: 6669523 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.8564. Min Act: -0.1700
Data Index: 2782121 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.8252. Min Act: -0.1700
Data Index: 24000 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7939. Min Act: -0.1700
Data Index: 7535315 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7939. Min Act: -0.1700
Data Index: 542922 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7627. Min Act: -0.1700
Data Index: 3754614 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7627. Min Act: -0.1700
Data Index: 7076780 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7627. Min Act: -0.1700
Data Index: 6969362 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7627. Min Act: -0.1700
Data Index: 1888312 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7627. Min Act: -0.1700
Data Index: 4804665 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 3810006 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 175709 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 5016294 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 7329893 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7314. Min Act: -0.1700
Data Index: 6528696 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7002. Min Act: -0.1700
Data Index: 8334841 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2314. Min Range: -6.2314
Max Act: 5.7002. Min Act: -0.1700
Data Index: 3533624 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19