Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1402 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.4391. Min Act: -0.1700
Data Index: 8635131 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.1266. Min Act: -0.1700
Data Index: 6712869 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.0953. Min Act: -0.1700
Data Index: 7314685 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.0953. Min Act: -0.1700
Data Index: 955484 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.0641. Min Act: -0.1700
Data Index: 4540133 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.0328. Min Act: -0.1700
Data Index: 2780633 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.0328. Min Act: -0.1700
Data Index: 4741555 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4391. Min Range: -5.4391
Max Act: 5.0016. Min Act: -0.1700
Data Index: 5272492 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.9391. Min Act: -0.1700
Data Index: 559689 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.9391. Min Act: -0.1700
Data Index: 4353666 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.9078. Min Act: -0.1700
Data Index: 6114561 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.9078. Min Act: -0.1700
Data Index: 8220877 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8766. Min Act: -0.1700
Data Index: 2825397 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8766. Min Act: -0.1700
Data Index: 6366442 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8766. Min Act: -0.1700
Data Index: 6835926 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8453. Min Act: -0.1700
Data Index: 765197 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8453. Min Act: -0.1700
Data Index: 3991608 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8453. Min Act: -0.1700
Data Index: 6989847 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8766. Min Act: -0.1700
Data Index: 8102179 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4391. Min Range: -5.4391
Max Act: 4.8141. Min Act: -0.1700
Data Index: 2737326 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19