Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3084 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.8443. Min Act: -0.1700
Data Index: 1135957 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.7818. Min Act: -0.1700
Data Index: 8818314 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.4693. Min Act: -0.1700
Data Index: 2834348 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.4693. Min Act: -0.1700
Data Index: 5998588 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.4068. Min Act: -0.1700
Data Index: 5558300 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.4068. Min Act: -0.1700
Data Index: 5560616 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.4068. Min Act: -0.1700
Data Index: 3184567 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.4068. Min Act: -0.1700
Data Index: 7451872 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.3443. Min Act: -0.1700
Data Index: 5767957 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.3443. Min Act: -0.1700
Data Index: 2726833 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.2818. Min Act: -0.1700
Data Index: 1231016 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.2818. Min Act: -0.1700
Data Index: 5090458 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.2193. Min Act: -0.1700
Data Index: 2485172 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.2193. Min Act: -0.1700
Data Index: 4605238 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.1568. Min Act: -0.1700
Data Index: 4926698 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.1568. Min Act: -0.1700
Data Index: 5985738 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.0943. Min Act: -0.1700
Data Index: 6216374 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.1568. Min Act: -0.1700
Data Index: 6274659 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.1568. Min Act: -0.1700
Data Index: 3331459 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8443. Min Range: -8.8443
Max Act: 8.1568. Min Act: -0.1700
Data Index: 2662097 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19