Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4289. Min Range: -6.4289
Max Act: 6.4289. Min Act: -0.1700
Data Index: 114884 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4289. Min Range: -6.4289
Max Act: 6.4289. Min Act: -0.1700
Data Index: 7935335 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4289. Min Range: -6.4289
Max Act: 6.3976. Min Act: -0.1700
Data Index: 4665813 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4289. Min Range: -6.4289
Max Act: 6.2101. Min Act: -0.1700
Data Index: 7624196 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4289. Min Range: -6.4289
Max Act: 6.1164. Min Act: -0.1700
Data Index: 2568011 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4289. Min Range: -6.4289
Max Act: 6.0226. Min Act: -0.1700
Data Index: 687494 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.9601. Min Act: -0.1700
Data Index: 1681839 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.9601. Min Act: -0.1700
Data Index: 60258 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.9289. Min Act: -0.1700
Data Index: 2725518 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.8039. Min Act: -0.1700
Data Index: 7579440 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.8351. Min Act: -0.1700
Data Index: 4764356 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.8039. Min Act: -0.1700
Data Index: 3690917 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.7726. Min Act: -0.1700
Data Index: 6404322 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.7726. Min Act: -0.1700
Data Index: 1718631 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.7414. Min Act: -0.1700
Data Index: 7742322 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.7101. Min Act: -0.1700
Data Index: 7345033 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.7414. Min Act: -0.1700
Data Index: 4551360 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.7101. Min Act: -0.1700
Data Index: 7490238 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.6789. Min Act: -0.1700
Data Index: 2619704 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4289. Min Range: -6.4289
Max Act: 5.6789. Min Act: -0.1700
Data Index: 8382563 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19