Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.4489. Min Act: -0.1700
Data Index: 3194103 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3673. Min Act: -0.1700
Data Index: 5475771 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3510. Min Act: -0.1700
Data Index: 5618397 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3837. Min Act: -0.1700
Data Index: 5604064 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3673. Min Act: -0.1700
Data Index: 1083363 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3510. Min Act: -0.1700
Data Index: 591942 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3346. Min Act: -0.1700
Data Index: 5442359 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3510. Min Act: -0.1700
Data Index: 5855262 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3346. Min Act: -0.1700
Data Index: 8421123 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3182. Min Act: -0.1700
Data Index: 1407549 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3182. Min Act: -0.1700
Data Index: 2332825 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3182. Min Act: -0.1700
Data Index: 5967665 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3017. Min Act: -0.1700
Data Index: 4750418 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.2853. Min Act: -0.1700
Data Index: 5545812 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3017. Min Act: -0.1700
Data Index: 5065042 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3017. Min Act: -0.1700
Data Index: 115382 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3182. Min Act: -0.1700
Data Index: 4182223 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3182. Min Act: -0.1700
Data Index: 1284641 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.3182. Min Act: -0.1700
Data Index: 3033943 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4489. Min Range: -2.4489
Max Act: 2.2853. Min Act: -0.1700
Data Index: 3154269 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19