Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4393 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0507. Min Range: -8.0507
Max Act: 8.0507. Min Act: -0.1700
Data Index: 5752351 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.9882. Min Act: -0.1700
Data Index: 6334374 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.9257. Min Act: -0.1700
Data Index: 2924093 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.8632. Min Act: -0.1700
Data Index: 7308404 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.8007. Min Act: -0.1700
Data Index: 4654604 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.8007. Min Act: -0.1700
Data Index: 3684419 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 4909628 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 2089252 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 3217623 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 1662623 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 7790326 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 7839520 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.6757. Min Act: -0.1700
Data Index: 2263334 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.7382. Min Act: -0.1700
Data Index: 6214595 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.6757. Min Act: -0.1700
Data Index: 7314574 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.6445. Min Act: -0.1700
Data Index: 7373778 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.6757. Min Act: -0.1700
Data Index: 5589198 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.6757. Min Act: -0.1700
Data Index: 8539261 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.6445. Min Act: -0.1700
Data Index: 6541646 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0507. Min Range: -8.0507
Max Act: 7.5820. Min Act: -0.1700
Data Index: 4427260 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19