Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5980 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0320. Min Range: -8.0320
Max Act: 8.0320. Min Act: -0.1700
Data Index: 242728 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.7195. Min Act: -0.1700
Data Index: 2937090 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.7195. Min Act: -0.1700
Data Index: 7315701 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.5632. Min Act: -0.1700
Data Index: 2436171 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.5632. Min Act: -0.1700
Data Index: 7155155 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.4695. Min Act: -0.1700
Data Index: 7134944 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.4382. Min Act: -0.1700
Data Index: 4184045 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.4382. Min Act: -0.1700
Data Index: 1728430 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.4070. Min Act: -0.1700
Data Index: 3842410 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.3132. Min Act: -0.1700
Data Index: 5011717 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.2195. Min Act: -0.1700
Data Index: 444877 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.1882. Min Act: -0.1700
Data Index: 2237806 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.1882. Min Act: -0.1700
Data Index: 6034413 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.1570. Min Act: -0.1700
Data Index: 3966134 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.1570. Min Act: -0.1700
Data Index: 1922617 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.1570. Min Act: -0.1700
Data Index: 6734311 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.1257. Min Act: -0.1700
Data Index: 4344095 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.0945. Min Act: -0.1700
Data Index: 1167133 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.0945. Min Act: -0.1700
Data Index: 4861418 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0320. Min Range: -8.0320
Max Act: 7.0632. Min Act: -0.1700
Data Index: 3714694 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19