Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0105. Min Range: -6.0105
Max Act: 6.0105. Min Act: -0.1700
Data Index: 4990901 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.9168. Min Act: -0.1700
Data Index: 6209917 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.9168. Min Act: -0.1700
Data Index: 8770630 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.8230. Min Act: -0.1700
Data Index: 1243090 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.8230. Min Act: -0.1700
Data Index: 3348533 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.7605. Min Act: -0.1700
Data Index: 7832961 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.7605. Min Act: -0.1700
Data Index: 2452512 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6668. Min Act: -0.1700
Data Index: 8130280 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6355. Min Act: -0.1700
Data Index: 1126208 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6355. Min Act: -0.1700
Data Index: 7014087 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6355. Min Act: -0.1700
Data Index: 3006992 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6043. Min Act: -0.1700
Data Index: 7994424 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6043. Min Act: -0.1700
Data Index: 4788522 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.6043. Min Act: -0.1700
Data Index: 371688 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.5730. Min Act: -0.1700
Data Index: 2903394 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.5418. Min Act: -0.1700
Data Index: 8661069 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.5418. Min Act: -0.1700
Data Index: 8704375 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.4793. Min Act: -0.1700
Data Index: 5628880 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.5105. Min Act: -0.1700
Data Index: 5342219 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0105. Min Range: -6.0105
Max Act: 5.4793. Min Act: -0.1700
Data Index: 6163702 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19