Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5627 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.5241. Min Act: -0.1700
Data Index: 6214497 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3831. Min Act: -0.1700
Data Index: 6545508 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3674. Min Act: -0.1700
Data Index: 6456775 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3360. Min Act: -0.1700
Data Index: 1625089 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3360. Min Act: -0.1700
Data Index: 660021 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3360. Min Act: -0.1700
Data Index: 4933438 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3046. Min Act: -0.1700
Data Index: 2756434 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.2889. Min Act: -0.1700
Data Index: 6684596 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3203. Min Act: -0.1700
Data Index: 2373379 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.3046. Min Act: -0.1700
Data Index: 4604594 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.2889. Min Act: -0.1700
Data Index: 4377757 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.2418. Min Act: -0.1700
Data Index: 203260 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.2418. Min Act: -0.1700
Data Index: 6204845 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1946. Min Act: -0.1700
Data Index: 8032402 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1789. Min Act: -0.1700
Data Index: 7639635 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1789. Min Act: -0.1700
Data Index: 823672 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1789. Min Act: -0.1700
Data Index: 6082135 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1632. Min Act: -0.1700
Data Index: 6196467 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1632. Min Act: -0.1700
Data Index: 7817570 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5241. Min Range: -3.5241
Max Act: 3.1632. Min Act: -0.1700
Data Index: 3758995 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19