Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.8181. Min Act: -0.1700
Data Index: 7544762 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.6931. Min Act: -0.1700
Data Index: 2659295 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.3806. Min Act: -0.1700
Data Index: 8678571 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.2556. Min Act: -0.1700
Data Index: 8124801 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.2244. Min Act: -0.1700
Data Index: 5911246 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.1931. Min Act: -0.1700
Data Index: 4376845 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.1306. Min Act: -0.1700
Data Index: 6634690 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.1306. Min Act: -0.1700
Data Index: 1724140 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.1306. Min Act: -0.1700
Data Index: 2255212 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.0681. Min Act: -0.1700
Data Index: 2706780 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.0681. Min Act: -0.1700
Data Index: 5624269 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.0369. Min Act: -0.1700
Data Index: 1731806 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.0369. Min Act: -0.1700
Data Index: 7301458 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5512197 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8181. Min Range: -6.8181
Max Act: 6.0056. Min Act: -0.1700
Data Index: 3042433 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8181. Min Range: -6.8181
Max Act: 5.9744. Min Act: -0.1700
Data Index: 8682717 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8181. Min Range: -6.8181
Max Act: 5.9431. Min Act: -0.1700
Data Index: 4092784 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8181. Min Range: -6.8181
Max Act: 5.9744. Min Act: -0.1700
Data Index: 6732101 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8181. Min Range: -6.8181
Max Act: 5.9119. Min Act: -0.1700
Data Index: 8284685 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8181. Min Range: -6.8181
Max Act: 5.9119. Min Act: -0.1700
Data Index: 3384282 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19