Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.6398. Min Act: -0.1700
Data Index: 7271238 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.3585. Min Act: -0.1700
Data Index: 619868 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.2335. Min Act: -0.1700
Data Index: 7271234 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.2023. Min Act: -0.1700
Data Index: 7271233 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.1710. Min Act: -0.1700
Data Index: 619867 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.2023. Min Act: -0.1700
Data Index: 1477465 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.1398. Min Act: -0.1700
Data Index: 1477464 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.1085. Min Act: -0.1700
Data Index: 619866 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.1085. Min Act: -0.1700
Data Index: 3499735 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0772. Min Act: -0.1700
Data Index: 4450090 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0772. Min Act: -0.1700
Data Index: 2205994 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0772. Min Act: -0.1700
Data Index: 7271239 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 6643750 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 7271235 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0460. Min Act: -0.1700
Data Index: 1799477 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0147. Min Act: -0.1700
Data Index: 835462 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0147. Min Act: -0.1700
Data Index: 7606610 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6398. Min Range: -4.6398
Max Act: 4.0147. Min Act: -0.1700
Data Index: 7271232 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6398. Min Range: -4.6398
Max Act: 3.9522. Min Act: -0.1700
Data Index: 5788170 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6398. Min Range: -4.6398
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6989899 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19