Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5202 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.2579. Min Act: -0.1700
Data Index: 7065904 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.1954. Min Act: -0.1700
Data Index: 5408403 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.1329. Min Act: -0.1700
Data Index: 679773 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.1329. Min Act: -0.1700
Data Index: 1398839 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.1016. Min Act: -0.1700
Data Index: 7270294 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.1016. Min Act: -0.1700
Data Index: 7750436 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0391. Min Act: -0.1700
Data Index: 3502697 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0704. Min Act: -0.1700
Data Index: 2478921 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0079. Min Act: -0.1700
Data Index: 8140532 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0079. Min Act: -0.1700
Data Index: 2978961 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0079. Min Act: -0.1700
Data Index: 6256616 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0391. Min Act: -0.1700
Data Index: 1974599 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2579. Min Range: -5.2579
Max Act: 5.0079. Min Act: -0.1700
Data Index: 2046481 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.9766. Min Act: -0.1700
Data Index: 256245 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.9454. Min Act: -0.1700
Data Index: 7941238 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.9454. Min Act: -0.1700
Data Index: 1012441 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.9141. Min Act: -0.1700
Data Index: 994793 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.9141. Min Act: -0.1700
Data Index: 7097450 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.8516. Min Act: -0.1700
Data Index: 5890413 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2579. Min Range: -5.2579
Max Act: 4.8516. Min Act: -0.1700
Data Index: 7132222 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19