Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3012 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.3546. Min Act: -0.1700
Data Index: 1797339 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.3233. Min Act: -0.1700
Data Index: 235880 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.2608. Min Act: -0.1700
Data Index: 5252505 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.2608. Min Act: -0.1700
Data Index: 5997844 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.2296. Min Act: -0.1700
Data Index: 5330311 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1671. Min Act: -0.1700
Data Index: 4001298 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1671. Min Act: -0.1700
Data Index: 6588869 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1358. Min Act: -0.1700
Data Index: 2308702 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 153857 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 5575477 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 2347676 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 6148168 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 3209904 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 4342124 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1358. Min Act: -0.1700
Data Index: 3129300 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 6119438 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.0733. Min Act: -0.1700
Data Index: 5273896 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.0733. Min Act: -0.1700
Data Index: 6066383 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.0733. Min Act: -0.1700
Data Index: 276217 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3546. Min Range: -6.3546
Max Act: 6.1046. Min Act: -0.1700
Data Index: 918601 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19