Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4001 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.8760. Min Act: -0.1700
Data Index: 4601165 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.5948. Min Act: -0.1700
Data Index: 8141033 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.5323. Min Act: -0.1700
Data Index: 2382286 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.4698. Min Act: -0.1700
Data Index: 2306746 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.4385. Min Act: -0.1700
Data Index: 5585252 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.4073. Min Act: -0.1700
Data Index: 5944793 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.3448. Min Act: -0.1700
Data Index: 1124961 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.3760. Min Act: -0.1700
Data Index: 2547433 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.3448. Min Act: -0.1700
Data Index: 2276638 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.3135. Min Act: -0.1700
Data Index: 4686084 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.2823. Min Act: -0.1700
Data Index: 7288047 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.2510. Min Act: -0.1700
Data Index: 8707514 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.2510. Min Act: -0.1700
Data Index: 1243036 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.2198. Min Act: -0.1700
Data Index: 6978459 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.2198. Min Act: -0.1700
Data Index: 4538364 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.1885. Min Act: -0.1700
Data Index: 910923 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.1885. Min Act: -0.1700
Data Index: 2920226 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.1885. Min Act: -0.1700
Data Index: 7415054 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.1573. Min Act: -0.1700
Data Index: 3028108 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8760. Min Range: -6.8760
Max Act: 6.1260. Min Act: -0.1700
Data Index: 2395320 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19