Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.6190. Min Act: -0.1700
Data Index: 1154808 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.5877. Min Act: -0.1700
Data Index: 5589112 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.5877. Min Act: -0.1700
Data Index: 4405576 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4457752 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4940. Min Act: -0.1700
Data Index: 8241414 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4940. Min Act: -0.1700
Data Index: 4028928 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4940. Min Act: -0.1700
Data Index: 3074425 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4940. Min Act: -0.1700
Data Index: 6662567 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4940. Min Act: -0.1700
Data Index: 6250699 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4627. Min Act: -0.1700
Data Index: 5236688 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4315. Min Act: -0.1700
Data Index: 4121482 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4002. Min Act: -0.1700
Data Index: 2217653 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4002. Min Act: -0.1700
Data Index: 4600080 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4002. Min Act: -0.1700
Data Index: 2808773 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4002. Min Act: -0.1700
Data Index: 2452788 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4002. Min Act: -0.1700
Data Index: 1581316 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.4002. Min Act: -0.1700
Data Index: 1524978 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.3690. Min Act: -0.1700
Data Index: 4479225 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.3377. Min Act: -0.1700
Data Index: 449066 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6190. Min Range: -5.6190
Max Act: 5.3377. Min Act: -0.1700
Data Index: 1288020 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19