Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.6773. Min Act: -0.1700
Data Index: 7876418 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.5836. Min Act: -0.1700
Data Index: 8345646 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.5523. Min Act: -0.1700
Data Index: 4461680 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.4273. Min Act: -0.1700
Data Index: 2253316 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.3648. Min Act: -0.1700
Data Index: 515378 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.3023. Min Act: -0.1700
Data Index: 1697458 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.2711. Min Act: -0.1700
Data Index: 7897762 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.2398. Min Act: -0.1700
Data Index: 5781617 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.1773. Min Act: -0.1700
Data Index: 4618916 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3596675 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3160234 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.1148. Min Act: -0.1700
Data Index: 1116126 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.0836. Min Act: -0.1700
Data Index: 3405792 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.0211. Min Act: -0.1700
Data Index: 1764361 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6773. Min Range: -5.6773
Max Act: 4.9898. Min Act: -0.1700
Data Index: 4387916 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6773. Min Range: -5.6773
Max Act: 5.0211. Min Act: -0.1700
Data Index: 4263159 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6773. Min Range: -5.6773
Max Act: 4.9898. Min Act: -0.1700
Data Index: 5975310 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6773. Min Range: -5.6773
Max Act: 4.9898. Min Act: -0.1700
Data Index: 109342 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6773. Min Range: -5.6773
Max Act: 4.9898. Min Act: -0.1700
Data Index: 7965215 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6773. Min Range: -5.6773
Max Act: 4.9898. Min Act: -0.1700
Data Index: 2341117 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19