Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5355 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.9327. Min Act: -0.1700
Data Index: 8798290 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.8077. Min Act: -0.1700
Data Index: 258384 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.8077. Min Act: -0.1700
Data Index: 5020744 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.7764. Min Act: -0.1700
Data Index: 6405990 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.7139. Min Act: -0.1700
Data Index: 2492619 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5889. Min Act: -0.1700
Data Index: 8744696 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5577. Min Act: -0.1700
Data Index: 3945637 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5577. Min Act: -0.1700
Data Index: 5737146 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5264. Min Act: -0.1700
Data Index: 6989937 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5577. Min Act: -0.1700
Data Index: 5293209 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5264. Min Act: -0.1700
Data Index: 4320394 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5264. Min Act: -0.1700
Data Index: 406662 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7813704 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5264. Min Act: -0.1700
Data Index: 1326092 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.4952. Min Act: -0.1700
Data Index: 5487928 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.4952. Min Act: -0.1700
Data Index: 1664633 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.4952. Min Act: -0.1700
Data Index: 7429254 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.4952. Min Act: -0.1700
Data Index: 2885881 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.5264. Min Act: -0.1700
Data Index: 7246300 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9327. Min Range: -5.9327
Max Act: 5.4952. Min Act: -0.1700
Data Index: 4686685 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19