Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 176 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6285. Min Range: -8.6285
Max Act: 8.6285. Min Act: -0.1700
Data Index: 1616078 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6285. Min Range: -8.6285
Max Act: 8.5660. Min Act: -0.1700
Data Index: 2827358 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6285. Min Range: -8.6285
Max Act: 8.4410. Min Act: -0.1700
Data Index: 8769452 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6285. Min Range: -8.6285
Max Act: 8.2535. Min Act: -0.1700
Data Index: 8088852 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6285. Min Range: -8.6285
Max Act: 8.2535. Min Act: -0.1700
Data Index: 471221 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.9723. Min Act: -0.1700
Data Index: 8412553 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.9723. Min Act: -0.1700
Data Index: 7255726 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.9723. Min Act: -0.1700
Data Index: 8412591 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.9410. Min Act: -0.1700
Data Index: 7047064 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.9098. Min Act: -0.1700
Data Index: 1389265 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.8785. Min Act: -0.1700
Data Index: 6857192 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7848. Min Act: -0.1700
Data Index: 8265868 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.8160. Min Act: -0.1700
Data Index: 8301807 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.8160. Min Act: -0.1700
Data Index: 6145761 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7848. Min Act: -0.1700
Data Index: 4939623 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7848. Min Act: -0.1700
Data Index: 207467 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7535. Min Act: -0.1700
Data Index: 6679081 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7535. Min Act: -0.1700
Data Index: 7688089 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7223. Min Act: -0.1700
Data Index: 1113059 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6285. Min Range: -8.6285
Max Act: 7.7535. Min Act: -0.1700
Data Index: 5539872 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19