Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4579 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0475. Min Range: -4.0475
Max Act: 4.0162. Min Act: -0.1700
Data Index: 8105601 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0475. Min Range: -4.0475
Max Act: 4.0475. Min Act: -0.1700
Data Index: 382065 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.9224. Min Act: -0.1700
Data Index: 5320815 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.9224. Min Act: -0.1700
Data Index: 6372829 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8755. Min Act: -0.1700
Data Index: 2887389 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8912. Min Act: -0.1700
Data Index: 7561241 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8755. Min Act: -0.1700
Data Index: 5435623 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8755. Min Act: -0.1700
Data Index: 6379900 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8912. Min Act: -0.1700
Data Index: 7563495 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8599. Min Act: -0.1700
Data Index: 1348225 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8443. Min Act: -0.1700
Data Index: 2025523 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8443. Min Act: -0.1700
Data Index: 7143253 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8286. Min Act: -0.1700
Data Index: 333017 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8286. Min Act: -0.1700
Data Index: 8377880 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8130. Min Act: -0.1700
Data Index: 124523 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8286. Min Act: -0.1700
Data Index: 4100067 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.8130. Min Act: -0.1700
Data Index: 3903212 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.7974. Min Act: -0.1700
Data Index: 5935494 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.7974. Min Act: -0.1700
Data Index: 6615734 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0475. Min Range: -4.0475
Max Act: 3.7974. Min Act: -0.1700
Data Index: 1157660 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19