Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.5333. Min Act: -0.1700
Data Index: 390565 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.2520. Min Act: -0.1700
Data Index: 7327261 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.2520. Min Act: -0.1700
Data Index: 4629942 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.0958. Min Act: -0.1700
Data Index: 3610308 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.0645. Min Act: -0.1700
Data Index: 2738769 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.0020. Min Act: -0.1700
Data Index: 7736523 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.0020. Min Act: -0.1700
Data Index: 7388348 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5333. Min Range: -5.5333
Max Act: 5.0020. Min Act: -0.1700
Data Index: 7682261 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1565860 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1622364 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8770. Min Act: -0.1700
Data Index: 8042298 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8770. Min Act: -0.1700
Data Index: 1947867 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8770. Min Act: -0.1700
Data Index: 8164455 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8770. Min Act: -0.1700
Data Index: 2081640 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8458. Min Act: -0.1700
Data Index: 1993797 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8458. Min Act: -0.1700
Data Index: 224781 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8145. Min Act: -0.1700
Data Index: 649132 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.7833. Min Act: -0.1700
Data Index: 5043396 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.8145. Min Act: -0.1700
Data Index: 1308371 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5333. Min Range: -5.5333
Max Act: 4.7833. Min Act: -0.1700
Data Index: 7769243 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19