Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2419 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.5315. Min Act: -0.1700
Data Index: 981864 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.3905. Min Act: -0.1700
Data Index: 3153689 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.3121. Min Act: -0.1700
Data Index: 5169295 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2964. Min Act: -0.1700
Data Index: 1447608 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2964. Min Act: -0.1700
Data Index: 4096397 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2650. Min Act: -0.1700
Data Index: 984498 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2964. Min Act: -0.1700
Data Index: 4435818 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2807. Min Act: -0.1700
Data Index: 18752 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2650. Min Act: -0.1700
Data Index: 8366137 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2178. Min Act: -0.1700
Data Index: 8038609 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2335. Min Act: -0.1700
Data Index: 3627964 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2492. Min Act: -0.1700
Data Index: 5749342 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2021. Min Act: -0.1700
Data Index: 5998097 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2021. Min Act: -0.1700
Data Index: 8480860 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.2021. Min Act: -0.1700
Data Index: 1060964 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.1864. Min Act: -0.1700
Data Index: 4352787 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.1864. Min Act: -0.1700
Data Index: 3181202 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.1706. Min Act: -0.1700
Data Index: 7669016 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.1706. Min Act: -0.1700
Data Index: 1388881 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5315. Min Range: -3.5315
Max Act: 3.1706. Min Act: -0.1700
Data Index: 2513168 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19