Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3973. Min Range: -9.3973
Max Act: 9.3973. Min Act: -0.1700
Data Index: 2340375 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 3320232 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8973. Min Act: -0.1700
Data Index: 4002380 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 7114402 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.8348. Min Act: -0.1700
Data Index: 4087798 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.7723. Min Act: -0.1700
Data Index: 2298669 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.7723. Min Act: -0.1700
Data Index: 5479239 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.7098. Min Act: -0.1700
Data Index: 2988545 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.6473. Min Act: -0.1700
Data Index: 7555400 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.5848. Min Act: -0.1700
Data Index: 5151703 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.5223. Min Act: -0.1700
Data Index: 3576687 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.5848. Min Act: -0.1700
Data Index: 6644994 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.5848. Min Act: -0.1700
Data Index: 5012993 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.5223. Min Act: -0.1700
Data Index: 5055446 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.5223. Min Act: -0.1700
Data Index: 33190 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.4598. Min Act: -0.1700
Data Index: 5377438 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.4598. Min Act: -0.1700
Data Index: 2107381 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.4598. Min Act: -0.1700
Data Index: 6158492 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.4598. Min Act: -0.1700
Data Index: 2988540 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3973. Min Range: -9.3973
Max Act: 8.4598. Min Act: -0.1700
Data Index: 3415465 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19