Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.6235. Min Act: -0.1700
Data Index: 5208383 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.4356. Min Act: -0.1700
Data Index: 2595546 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.3258. Min Act: -0.1700
Data Index: 7929799 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.3101. Min Act: -0.1700
Data Index: 5951417 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2944. Min Act: -0.1700
Data Index: 7966381 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2787. Min Act: -0.1700
Data Index: 2585298 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2473. Min Act: -0.1700
Data Index: 7731445 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2630. Min Act: -0.1700
Data Index: 2945232 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2473. Min Act: -0.1700
Data Index: 4740008 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2473. Min Act: -0.1700
Data Index: 2798174 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2473. Min Act: -0.1700
Data Index: 8096316 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2316. Min Act: -0.1700
Data Index: 7976314 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2159. Min Act: -0.1700
Data Index: 5115983 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2001. Min Act: -0.1700
Data Index: 1530608 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.1844. Min Act: -0.1700
Data Index: 1385690 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.1844. Min Act: -0.1700
Data Index: 7159700 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.1844. Min Act: -0.1700
Data Index: 4700083 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.1687. Min Act: -0.1700
Data Index: 7089840 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.2001. Min Act: -0.1700
Data Index: 534217 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6235. Min Range: -3.6235
Max Act: 3.1687. Min Act: -0.1700
Data Index: 5522783 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19