Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4243. Min Range: -6.4243
Max Act: 6.4243. Min Act: -0.1700
Data Index: 6503908 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4243. Min Range: -6.4243
Max Act: 6.1431. Min Act: -0.1700
Data Index: 6180217 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4243. Min Range: -6.4243
Max Act: 6.0493. Min Act: -0.1700
Data Index: 6529280 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4243. Min Range: -6.4243
Max Act: 6.0181. Min Act: -0.1700
Data Index: 7058278 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.9556. Min Act: -0.1700
Data Index: 8801568 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.9868. Min Act: -0.1700
Data Index: 6782807 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.9243. Min Act: -0.1700
Data Index: 8304872 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3498044 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.8931. Min Act: -0.1700
Data Index: 6675874 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.8618. Min Act: -0.1700
Data Index: 4493437 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.8618. Min Act: -0.1700
Data Index: 7628139 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.8306. Min Act: -0.1700
Data Index: 5495109 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.8306. Min Act: -0.1700
Data Index: 7134479 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7993. Min Act: -0.1700
Data Index: 1723025 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7681. Min Act: -0.1700
Data Index: 1486918 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7681. Min Act: -0.1700
Data Index: 4697234 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7368. Min Act: -0.1700
Data Index: 1787796 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7368. Min Act: -0.1700
Data Index: 6519358 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7368. Min Act: -0.1700
Data Index: 7277302 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4243. Min Range: -6.4243
Max Act: 5.7056. Min Act: -0.1700
Data Index: 4376718 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19