Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0248. Min Range: -5.0248
Max Act: 5.0248. Min Act: -0.1700
Data Index: 7040894 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0248. Min Range: -5.0248
Max Act: 5.0248. Min Act: -0.1700
Data Index: 5527088 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.9310. Min Act: -0.1700
Data Index: 8592806 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.8060. Min Act: -0.1700
Data Index: 7446122 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7747. Min Act: -0.1700
Data Index: 7425408 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.8372. Min Act: -0.1700
Data Index: 5586050 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.8060. Min Act: -0.1700
Data Index: 5814664 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7747. Min Act: -0.1700
Data Index: 8603868 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7747. Min Act: -0.1700
Data Index: 1968248 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 5232430 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 6845956 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7122. Min Act: -0.1700
Data Index: 4208935 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 3634689 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7122. Min Act: -0.1700
Data Index: 2938093 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7122. Min Act: -0.1700
Data Index: 6733370 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7435. Min Act: -0.1700
Data Index: 7716980 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.7122. Min Act: -0.1700
Data Index: 8675661 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6810. Min Act: -0.1700
Data Index: 4630620 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6810. Min Act: -0.1700
Data Index: 6615902 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0248. Min Range: -5.0248
Max Act: 4.6810. Min Act: -0.1700
Data Index: 2909928 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19