Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.5105. Min Act: -0.1700
Data Index: 6028206 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.4793. Min Act: -0.1700
Data Index: 1341403 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.4168. Min Act: -0.1700
Data Index: 6712749 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.3230. Min Act: -0.1700
Data Index: 2233338 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.3230. Min Act: -0.1700
Data Index: 1865772 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.2293. Min Act: -0.1700
Data Index: 8590636 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.2918. Min Act: -0.1700
Data Index: 8590637 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.2293. Min Act: -0.1700
Data Index: 5357193 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.2605. Min Act: -0.1700
Data Index: 1656158 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1980. Min Act: -0.1700
Data Index: 6004570 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1980. Min Act: -0.1700
Data Index: 3151016 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1980. Min Act: -0.1700
Data Index: 6622083 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1668. Min Act: -0.1700
Data Index: 2505145 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1668. Min Act: -0.1700
Data Index: 1656159 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1668. Min Act: -0.1700
Data Index: 7588649 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1668. Min Act: -0.1699
Data Index: 1194954 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1355. Min Act: -0.1700
Data Index: 1904962 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1355. Min Act: -0.1700
Data Index: 5662103 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1355. Min Act: -0.1700
Data Index: 6868695 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5105. Min Range: -6.5105
Max Act: 6.1355. Min Act: -0.1700
Data Index: 3195088 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19