Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.9964. Min Act: -0.1700
Data Index: 2521459 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.8402. Min Act: -0.1700
Data Index: 7520158 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.7777. Min Act: -0.1700
Data Index: 7520162 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.7152. Min Act: -0.1700
Data Index: 4119764 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.6839. Min Act: -0.1700
Data Index: 2319821 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.6527. Min Act: -0.1700
Data Index: 1595460 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.6214. Min Act: -0.1700
Data Index: 7520166 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.5589. Min Act: -0.1700
Data Index: 6549655 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4964. Min Act: -0.1700
Data Index: 2036454 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.5277. Min Act: -0.1700
Data Index: 4255373 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4964. Min Act: -0.1700
Data Index: 8435580 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4964. Min Act: -0.1700
Data Index: 2175398 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4964. Min Act: -0.1700
Data Index: 7809294 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4339. Min Act: -0.1700
Data Index: 3690832 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4652. Min Act: -0.1700
Data Index: 568570 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4652. Min Act: -0.1700
Data Index: 2945978 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.4339. Min Act: -0.1700
Data Index: 4304675 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.3714. Min Act: -0.1700
Data Index: 7256185 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.3402. Min Act: -0.1700
Data Index: 3165017 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9964. Min Range: -7.9964
Max Act: 7.3089. Min Act: -0.1700
Data Index: 3717628 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19