Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.2780. Min Act: -0.1700
Data Index: 2410257 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.1843. Min Act: -0.1700
Data Index: 5617576 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.1530. Min Act: -0.1700
Data Index: 2955538 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.1217. Min Act: -0.1700
Data Index: 4695439 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.1217. Min Act: -0.1700
Data Index: 3763947 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.0592. Min Act: -0.1700
Data Index: 1646136 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.0592. Min Act: -0.1700
Data Index: 3179365 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2780. Min Range: -4.2780
Max Act: 4.0280. Min Act: -0.1700
Data Index: 1850419 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9967. Min Act: -0.1700
Data Index: 8702037 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9967. Min Act: -0.1700
Data Index: 2192184 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9967. Min Act: -0.1700
Data Index: 195328 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9967. Min Act: -0.1700
Data Index: 7444726 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9655. Min Act: -0.1700
Data Index: 4818275 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9342. Min Act: -0.1700
Data Index: 3855198 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9342. Min Act: -0.1700
Data Index: 6731565 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9342. Min Act: -0.1700
Data Index: 2871793 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9342. Min Act: -0.1700
Data Index: 3637294 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9342. Min Act: -0.1700
Data Index: 3352605 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9029. Min Act: -0.1700
Data Index: 5837652 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2780. Min Range: -4.2780
Max Act: 3.9655. Min Act: -0.1700
Data Index: 8365885 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19