Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2193. Min Range: -6.2193
Max Act: 6.2193. Min Act: -0.1700
Data Index: 3324215 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.9380. Min Act: -0.1700
Data Index: 367418 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.9380. Min Act: -0.1700
Data Index: 63308 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.9380. Min Act: -0.1700
Data Index: 924180 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.6568. Min Act: -0.1700
Data Index: 8313178 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.6568. Min Act: -0.1700
Data Index: 6269829 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5943. Min Act: -0.1700
Data Index: 186503 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5943. Min Act: -0.1700
Data Index: 6641224 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5630. Min Act: -0.1700
Data Index: 8636317 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5318. Min Act: -0.1700
Data Index: 3960009 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5318. Min Act: -0.1700
Data Index: 3004601 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5630. Min Act: -0.1700
Data Index: 147924 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5005. Min Act: -0.1700
Data Index: 6965791 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5005. Min Act: -0.1700
Data Index: 6929095 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5005. Min Act: -0.1700
Data Index: 6440420 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.4693. Min Act: -0.1700
Data Index: 4354661 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.4380. Min Act: -0.1700
Data Index: 5616598 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.4693. Min Act: -0.1700
Data Index: 4746180 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.4693. Min Act: -0.1700
Data Index: 1557978 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2193. Min Range: -6.2193
Max Act: 5.5005. Min Act: -0.1700
Data Index: 64420 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19