Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 680 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.7558. Min Act: -0.1700
Data Index: 1325966 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.6621. Min Act: -0.1700
Data Index: 408511 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.5058. Min Act: -0.1700
Data Index: 3644001 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.4746. Min Act: -0.1700
Data Index: 4808550 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.4433. Min Act: -0.1700
Data Index: 2273824 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.4121. Min Act: -0.1700
Data Index: 7303036 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2871. Min Act: -0.1700
Data Index: 5504211 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2871. Min Act: -0.1700
Data Index: 6817438 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.3183. Min Act: -0.1700
Data Index: 7359414 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.3183. Min Act: -0.1700
Data Index: 8439766 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.3183. Min Act: -0.1700
Data Index: 4789944 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2871. Min Act: -0.1700
Data Index: 3071136 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.3183. Min Act: -0.1700
Data Index: 2864055 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2871. Min Act: -0.1700
Data Index: 2216474 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2871. Min Act: -0.1700
Data Index: 3936347 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2246. Min Act: -0.1700
Data Index: 574216 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2246. Min Act: -0.1700
Data Index: 815361 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2246. Min Act: -0.1700
Data Index: 3676585 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2246. Min Act: -0.1700
Data Index: 4930871 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7558. Min Range: -5.7558
Max Act: 5.2246. Min Act: -0.1700
Data Index: 5231064 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19