Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3322 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.6348. Min Act: -0.1700
Data Index: 5765882 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.6035. Min Act: -0.1700
Data Index: 8441184 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.5723. Min Act: -0.1700
Data Index: 2982978 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.5410. Min Act: -0.1700
Data Index: 2982977 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.5098. Min Act: -0.1700
Data Index: 1205127 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4473. Min Act: -0.1700
Data Index: 1205128 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.4160. Min Act: -0.1700
Data Index: 5763342 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 8441168 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 2982976 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3848. Min Act: -0.1700
Data Index: 1205129 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3535. Min Act: -0.1700
Data Index: 1316107 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3535. Min Act: -0.1700
Data Index: 5177311 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3223. Min Act: -0.1700
Data Index: 8441171 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.3535. Min Act: -0.1700
Data Index: 3395794 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.2598. Min Act: -0.1700
Data Index: 4653747 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.2598. Min Act: -0.1700
Data Index: 7610605 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.2910. Min Act: -0.1700
Data Index: 1089287 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.2598. Min Act: -0.1700
Data Index: 1726254 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.2598. Min Act: -0.1700
Data Index: 3200075 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6348. Min Range: -4.6348
Max Act: 4.2598. Min Act: -0.1700
Data Index: 2010314 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19