Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.5755. Min Act: -0.1700
Data Index: 1073275 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.4818. Min Act: -0.1700
Data Index: 3323479 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.4505. Min Act: -0.1700
Data Index: 6658194 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.3255. Min Act: -0.1700
Data Index: 5981224 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.3568. Min Act: -0.1700
Data Index: 3882945 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2943. Min Act: -0.1700
Data Index: 563440 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2630. Min Act: -0.1700
Data Index: 8710401 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2318. Min Act: -0.1700
Data Index: 7854665 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2318. Min Act: -0.1700
Data Index: 1073274 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2005. Min Act: -0.1700
Data Index: 7854664 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3561619 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1073271 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.2005. Min Act: -0.1700
Data Index: 1073277 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.1068. Min Act: -0.1700
Data Index: 1073272 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.1068. Min Act: -0.1700
Data Index: 4792169 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.1068. Min Act: -0.1700
Data Index: 1923207 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.0755. Min Act: -0.1700
Data Index: 4592560 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.0755. Min Act: -0.1700
Data Index: 3536074 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.1380. Min Act: -0.1700
Data Index: 7434417 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5755. Min Range: -5.5755
Max Act: 5.0755. Min Act: -0.1700
Data Index: 4592159 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19