Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.3825. Min Act: -0.1700
Data Index: 4871146 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.2262. Min Act: -0.1700
Data Index: 3855293 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1637. Min Act: -0.1700
Data Index: 1989300 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 2006331 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1325. Min Act: -0.1700
Data Index: 3386863 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1325. Min Act: -0.1700
Data Index: 62154 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1325. Min Act: -0.1700
Data Index: 8214193 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1637. Min Act: -0.1700
Data Index: 4469469 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 6764867 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 4162359 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 1267253 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 2553316 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0700. Min Act: -0.1700
Data Index: 2020595 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 231610 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0700. Min Act: -0.1700
Data Index: 4148764 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0700. Min Act: -0.1700
Data Index: 1319945 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0387. Min Act: -0.1700
Data Index: 1012191 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.1012. Min Act: -0.1700
Data Index: 62161 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0700. Min Act: -0.1700
Data Index: 4965768 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3825. Min Range: -5.3825
Max Act: 5.0700. Min Act: -0.1700
Data Index: 1908445 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19