Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.8623. Min Act: -0.1700
Data Index: 3636814 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.6748. Min Act: -0.1700
Data Index: 8698855 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.6123. Min Act: -0.1700
Data Index: 6868518 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.5498. Min Act: -0.1700
Data Index: 6055448 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.4873. Min Act: -0.1700
Data Index: 1935004 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.4873. Min Act: -0.1700
Data Index: 5931401 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.4873. Min Act: -0.1700
Data Index: 8541048 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.4873. Min Act: -0.1700
Data Index: 1881553 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.4873. Min Act: -0.1700
Data Index: 1281393 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.3623. Min Act: -0.1700
Data Index: 6836820 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2998. Min Act: -0.1700
Data Index: 6149695 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.3623. Min Act: -0.1700
Data Index: 6346658 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2998. Min Act: -0.1700
Data Index: 6813055 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2998. Min Act: -0.1700
Data Index: 4251649 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2998. Min Act: -0.1700
Data Index: 5579619 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2373. Min Act: -0.1700
Data Index: 4509532 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2373. Min Act: -0.1700
Data Index: 3051600 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.2373. Min Act: -0.1700
Data Index: 5125565 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.1748. Min Act: -0.1700
Data Index: 6346655 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8623. Min Range: -9.8623
Max Act: 9.1748. Min Act: -0.1700
Data Index: 135294 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19