Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.5429. Min Act: -0.1700
Data Index: 6569653 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.4491. Min Act: -0.1700
Data Index: 3099104 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.4491. Min Act: -0.1700
Data Index: 900047 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.3554. Min Act: -0.1700
Data Index: 465959 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.3866. Min Act: -0.1700
Data Index: 4272338 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.3241. Min Act: -0.1700
Data Index: 3871889 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.2929. Min Act: -0.1700
Data Index: 6661613 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.2929. Min Act: -0.1700
Data Index: 4822975 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.2616. Min Act: -0.1700
Data Index: 2243898 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.2304. Min Act: -0.1700
Data Index: 2218572 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.2304. Min Act: -0.1700
Data Index: 3363377 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1991. Min Act: -0.1700
Data Index: 3733592 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1991. Min Act: -0.1700
Data Index: 1303431 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1679. Min Act: -0.1700
Data Index: 4251747 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1679. Min Act: -0.1700
Data Index: 1443218 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1679. Min Act: -0.1700
Data Index: 7546554 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1366. Min Act: -0.1700
Data Index: 1897274 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1054. Min Act: -0.1700
Data Index: 7410564 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1366. Min Act: -0.1700
Data Index: 1401145 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5429. Min Range: -6.5429
Max Act: 6.1366. Min Act: -0.1700
Data Index: 6341834 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19