Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2243 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.6286. Min Act: -0.1700
Data Index: 8820387 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.5036. Min Act: -0.1700
Data Index: 4749340 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.4723. Min Act: -0.1700
Data Index: 4121313 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.4411. Min Act: -0.1700
Data Index: 2405962 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.3161. Min Act: -0.1700
Data Index: 718661 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.3161. Min Act: -0.1700
Data Index: 6599283 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.2536. Min Act: -0.1700
Data Index: 1354563 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.2536. Min Act: -0.1700
Data Index: 1843513 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5876181 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.2223. Min Act: -0.1700
Data Index: 5873003 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.2223. Min Act: -0.1700
Data Index: 4434470 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.2223. Min Act: -0.1700
Data Index: 7947624 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1911. Min Act: -0.1700
Data Index: 718676 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1598. Min Act: -0.1700
Data Index: 8484046 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1286. Min Act: -0.1700
Data Index: 5145888 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1286. Min Act: -0.1700
Data Index: 8697312 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1598. Min Act: -0.1700
Data Index: 6138179 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1598. Min Act: -0.1700
Data Index: 5386370 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1598. Min Act: -0.1700
Data Index: 4512405 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6286. Min Range: -5.6286
Max Act: 5.1286. Min Act: -0.1700
Data Index: 462133 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19