Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.1862. Min Act: -0.1700
Data Index: 5770778 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.1862. Min Act: -0.1700
Data Index: 2066813 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.0925. Min Act: -0.1700
Data Index: 2512828 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.0925. Min Act: -0.1700
Data Index: 3030438 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.0300. Min Act: -0.1700
Data Index: 866386 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.0300. Min Act: -0.1700
Data Index: 6827272 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.0300. Min Act: -0.1700
Data Index: 7115731 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1862. Min Range: -5.1862
Max Act: 5.0300. Min Act: -0.1700
Data Index: 3607344 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9675. Min Act: -0.1700
Data Index: 4066713 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9987. Min Act: -0.1700
Data Index: 3406864 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9675. Min Act: -0.1700
Data Index: 1774323 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9675. Min Act: -0.1700
Data Index: 801627 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9362. Min Act: -0.1700
Data Index: 1187414 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9362. Min Act: -0.1700
Data Index: 7634465 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9362. Min Act: -0.1700
Data Index: 3976058 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9362. Min Act: -0.1700
Data Index: 1448764 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9050. Min Act: -0.1700
Data Index: 2812647 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.9050. Min Act: -0.1700
Data Index: 1445543 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.8737. Min Act: -0.1700
Data Index: 2579028 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1862. Min Range: -5.1862
Max Act: 4.8737. Min Act: -0.1700
Data Index: 2784855 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19