Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3363 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4042299 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.4112. Min Act: -0.1700
Data Index: 45877 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.3175. Min Act: -0.1700
Data Index: 7633762 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2862. Min Act: -0.1700
Data Index: 1493356 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2862. Min Act: -0.1700
Data Index: 3523759 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2550. Min Act: -0.1700
Data Index: 4578946 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2550. Min Act: -0.1700
Data Index: 7993610 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2550. Min Act: -0.1700
Data Index: 8130681 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2237. Min Act: -0.1700
Data Index: 2900904 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2237. Min Act: -0.1700
Data Index: 5770964 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1925. Min Act: -0.1700
Data Index: 7191169 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1925. Min Act: -0.1700
Data Index: 1769588 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1925. Min Act: -0.1700
Data Index: 6914541 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.2237. Min Act: -0.1700
Data Index: 8681560 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1612. Min Act: -0.1700
Data Index: 2195276 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1612. Min Act: -0.1700
Data Index: 746026 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1612. Min Act: -0.1700
Data Index: 5287140 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1300. Min Act: -0.1700
Data Index: 2609416 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1300. Min Act: -0.1700
Data Index: 2810552 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6300. Min Range: -5.6300
Max Act: 5.1300. Min Act: -0.1700
Data Index: 5551027 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19