Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.7470. Min Act: -0.1700
Data Index: 3657735 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.7158. Min Act: -0.1700
Data Index: 710329 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.6845. Min Act: -0.1700
Data Index: 4548970 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.6533. Min Act: -0.1700
Data Index: 1109511 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.6220. Min Act: -0.1700
Data Index: 2036634 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.5908. Min Act: -0.1700
Data Index: 7244770 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.5908. Min Act: -0.1700
Data Index: 8254621 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.5908. Min Act: -0.1700
Data Index: 5875643 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.5595. Min Act: -0.1700
Data Index: 3672138 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.5283. Min Act: -0.1700
Data Index: 4576311 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.5283. Min Act: -0.1700
Data Index: 6142226 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.4970. Min Act: -0.1700
Data Index: 6702267 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.4658. Min Act: -0.1700
Data Index: 5171367 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.4658. Min Act: -0.1700
Data Index: 6817449 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.4345. Min Act: -0.1700
Data Index: 7511230 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.4345. Min Act: -0.1700
Data Index: 7339281 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.3408. Min Act: -0.1700
Data Index: 2649547 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.3408. Min Act: -0.1700
Data Index: 3176861 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.3720. Min Act: -0.1700
Data Index: 1312669 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7470. Min Range: -6.7470
Max Act: 6.3095. Min Act: -0.1700
Data Index: 1677032 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19