Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2334. Min Range: -6.2334
Max Act: 6.2334. Min Act: -0.1700
Data Index: 11047 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2334. Min Range: -6.2334
Max Act: 6.2022. Min Act: -0.1700
Data Index: 2258430 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2334. Min Range: -6.2334
Max Act: 6.0772. Min Act: -0.1700
Data Index: 4258005 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2334. Min Range: -6.2334
Max Act: 6.0147. Min Act: -0.1700
Data Index: 1189630 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.9834. Min Act: -0.1700
Data Index: 6433273 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.9522. Min Act: -0.1700
Data Index: 3788781 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.8584. Min Act: -0.1700
Data Index: 2520038 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1109511 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.8584. Min Act: -0.1700
Data Index: 2596660 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.8584. Min Act: -0.1700
Data Index: 4665686 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.8272. Min Act: -0.1700
Data Index: 662810 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.7959. Min Act: -0.1700
Data Index: 1223304 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.7647. Min Act: -0.1700
Data Index: 2199112 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.7334. Min Act: -0.1700
Data Index: 2611710 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.7022. Min Act: -0.1700
Data Index: 1444945 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.6709. Min Act: -0.1700
Data Index: 1636841 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.6709. Min Act: -0.1700
Data Index: 7469365 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.6397. Min Act: -0.1700
Data Index: 1589449 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.6397. Min Act: -0.1700
Data Index: 6296437 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2334. Min Range: -6.2334
Max Act: 5.6397. Min Act: -0.1700
Data Index: 6011737 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19