Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5004 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.8586. Min Act: -0.1700
Data Index: 8442631 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.8273. Min Act: -0.1700
Data Index: 5423519 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.8273. Min Act: -0.1700
Data Index: 4089337 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7804. Min Act: -0.1700
Data Index: 5788275 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7961. Min Act: -0.1700
Data Index: 3174453 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7648. Min Act: -0.1700
Data Index: 8691417 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7492. Min Act: -0.1700
Data Index: 8324230 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7335. Min Act: -0.1700
Data Index: 2394725 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7022. Min Act: -0.1700
Data Index: 8448785 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6866. Min Act: -0.1700
Data Index: 967295 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6709. Min Act: -0.1700
Data Index: 1883954 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.7022. Min Act: -0.1700
Data Index: 747761 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6709. Min Act: -0.1700
Data Index: 3350166 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6866. Min Act: -0.1700
Data Index: 4972999 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6709. Min Act: -0.1700
Data Index: 8135578 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6396. Min Act: -0.1700
Data Index: 7145767 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6553. Min Act: -0.1700
Data Index: 7827177 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6553. Min Act: -0.1700
Data Index: 2393000 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6396. Min Act: -0.1700
Data Index: 1167077 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8586. Min Range: -3.8586
Max Act: 3.6240. Min Act: -0.1700
Data Index: 2645425 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19