Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 592 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.6392. Min Act: -0.1700
Data Index: 5881391 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.5767. Min Act: -0.1700
Data Index: 3495465 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.6079. Min Act: -0.1700
Data Index: 2523953 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.5767. Min Act: -0.1700
Data Index: 2449583 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.5142. Min Act: -0.1700
Data Index: 2523954 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.4517. Min Act: -0.1700
Data Index: 5780000 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.4204. Min Act: -0.1700
Data Index: 3495467 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.4204. Min Act: -0.1700
Data Index: 5881392 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.3892. Min Act: -0.1700
Data Index: 5881389 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.3892. Min Act: -0.1700
Data Index: 1622477 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.3579. Min Act: -0.1700
Data Index: 2523952 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.3267. Min Act: -0.1700
Data Index: 5881390 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.3267. Min Act: -0.1700
Data Index: 3444870 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.3267. Min Act: -0.1700
Data Index: 6520478 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.2954. Min Act: -0.1700
Data Index: 3252953 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.2954. Min Act: -0.1700
Data Index: 426529 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.2954. Min Act: -0.1700
Data Index: 3495464 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.2642. Min Act: -0.1700
Data Index: 3321991 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.2642. Min Act: -0.1700
Data Index: 7133717 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6392. Min Range: -5.6392
Max Act: 5.2642. Min Act: -0.1700
Data Index: 229840 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19