Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5979 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3286. Min Range: -5.3286
Max Act: 5.3286. Min Act: -0.1700
Data Index: 4451995 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3286. Min Range: -5.3286
Max Act: 5.3286. Min Act: -0.1700
Data Index: 3270283 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3286. Min Range: -5.3286
Max Act: 5.0474. Min Act: -0.1700
Data Index: 2177548 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.9536. Min Act: -0.1700
Data Index: 6644396 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.9224. Min Act: -0.1700
Data Index: 5337586 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.8286. Min Act: -0.1700
Data Index: 2893816 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.8286. Min Act: -0.1700
Data Index: 8191307 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7974. Min Act: -0.1700
Data Index: 7598104 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7974. Min Act: -0.1700
Data Index: 6316492 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7974. Min Act: -0.1700
Data Index: 2954367 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7661. Min Act: -0.1700
Data Index: 4293540 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7661. Min Act: -0.1700
Data Index: 5228345 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7661. Min Act: -0.1700
Data Index: 15853 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7349. Min Act: -0.1700
Data Index: 5321790 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7349. Min Act: -0.1700
Data Index: 2321476 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7036. Min Act: -0.1700
Data Index: 4501563 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.7036. Min Act: -0.1700
Data Index: 7474449 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.6724. Min Act: -0.1700
Data Index: 3376099 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.6724. Min Act: -0.1700
Data Index: 1337959 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3286. Min Range: -5.3286
Max Act: 4.6724. Min Act: -0.1700
Data Index: 2127669 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19