Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.3243. Min Act: -0.1700
Data Index: 7392828 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.3243. Min Act: -0.1700
Data Index: 3640790 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.2306. Min Act: -0.1700
Data Index: 6800663 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.1056. Min Act: -0.1700
Data Index: 4117722 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.1056. Min Act: -0.1700
Data Index: 1198000 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.0743. Min Act: -0.1700
Data Index: 7672067 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.0431. Min Act: -0.1700
Data Index: 1594762 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.0431. Min Act: -0.1700
Data Index: 6832751 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.0431. Min Act: -0.1700
Data Index: 504199 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.0118. Min Act: -0.1700
Data Index: 66851 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3243. Min Range: -6.3243
Max Act: 6.0118. Min Act: -0.1700
Data Index: 6065561 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.9806. Min Act: -0.1700
Data Index: 2324610 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.9493. Min Act: -0.1700
Data Index: 7385744 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.9181. Min Act: -0.1700
Data Index: 7310445 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.9181. Min Act: -0.1700
Data Index: 3082486 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.9181. Min Act: -0.1700
Data Index: 1335579 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.8868. Min Act: -0.1700
Data Index: 571348 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.8868. Min Act: -0.1700
Data Index: 1323856 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.8243. Min Act: -0.1700
Data Index: 7874224 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3243. Min Range: -6.3243
Max Act: 5.7618. Min Act: -0.1700
Data Index: 6018935 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19