Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3691. Min Range: -6.3691
Max Act: 6.3691. Min Act: -0.1700
Data Index: 1037693 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3691. Min Range: -6.3691
Max Act: 6.1816. Min Act: -0.1700
Data Index: 5925335 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3691. Min Range: -6.3691
Max Act: 6.1191. Min Act: -0.1700
Data Index: 8595596 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3691. Min Range: -6.3691
Max Act: 6.0254. Min Act: -0.1700
Data Index: 7169089 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.9629. Min Act: -0.1700
Data Index: 7161476 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.9004. Min Act: -0.1700
Data Index: 4293721 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8691. Min Act: -0.1700
Data Index: 1496 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.9316. Min Act: -0.1700
Data Index: 3427148 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.9004. Min Act: -0.1700
Data Index: 8194760 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.9004. Min Act: -0.1700
Data Index: 4517788 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8691. Min Act: -0.1700
Data Index: 6356481 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8691. Min Act: -0.1700
Data Index: 2871694 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8691. Min Act: -0.1700
Data Index: 112774 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8379. Min Act: -0.1700
Data Index: 6704166 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8379. Min Act: -0.1700
Data Index: 7579495 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.7754. Min Act: -0.1700
Data Index: 7348116 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.7754. Min Act: -0.1700
Data Index: 7161480 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.7754. Min Act: -0.1700
Data Index: 6967705 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.8066. Min Act: -0.1700
Data Index: 3775006 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3691. Min Range: -6.3691
Max Act: 5.7441. Min Act: -0.1700
Data Index: 5202292 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19