Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.4066. Min Act: -0.1700
Data Index: 6816250 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.4066. Min Act: -0.1700
Data Index: 4949815 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.3129. Min Act: -0.1700
Data Index: 351878 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 4316216 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.3129. Min Act: -0.1700
Data Index: 4469153 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2816. Min Act: -0.1700
Data Index: 4611490 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1879. Min Act: -0.1700
Data Index: 7687253 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 4704103 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 716518 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 2313371 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 1108145 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.2191. Min Act: -0.1700
Data Index: 7464242 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 5373889 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1879. Min Act: -0.1700
Data Index: 7017854 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1879. Min Act: -0.1700
Data Index: 1399222 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1879. Min Act: -0.1700
Data Index: 3613424 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1879. Min Act: -0.1700
Data Index: 6406363 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 6669474 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 5641466 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4066. Min Range: -5.4066
Max Act: 5.1566. Min Act: -0.1700
Data Index: 2066024 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19