Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4992 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.9105. Min Act: -0.1700
Data Index: 1552916 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8168. Min Act: -0.1700
Data Index: 8534392 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 3852331 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 8764723 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7543. Min Act: -0.1700
Data Index: 3707493 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7543. Min Act: -0.1700
Data Index: 1991736 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 1744627 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 4143413 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6605. Min Act: -0.1700
Data Index: 7332881 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6605. Min Act: -0.1700
Data Index: 8756958 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6605. Min Act: -0.1700
Data Index: 6571331 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6293. Min Act: -0.1700
Data Index: 5232719 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6293. Min Act: -0.1700
Data Index: 4810294 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6293. Min Act: -0.1700
Data Index: 4624746 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6293. Min Act: -0.1700
Data Index: 8430259 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7451868 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.5668. Min Act: -0.1700
Data Index: 6268156 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.5355. Min Act: -0.1700
Data Index: 5607848 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.5355. Min Act: -0.1700
Data Index: 2974555 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.5043. Min Act: -0.1700
Data Index: 6732152 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19