Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4805 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0176. Min Range: -6.0176
Max Act: 6.0176. Min Act: -0.1700
Data Index: 5041953 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4628504 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.7989. Min Act: -0.1700
Data Index: 2989137 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.6739. Min Act: -0.1700
Data Index: 1961708 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.6114. Min Act: -0.1700
Data Index: 1207475 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.6114. Min Act: -0.1700
Data Index: 1716700 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5801. Min Act: -0.1700
Data Index: 8502108 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7039640 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4190261 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5489. Min Act: -0.1700
Data Index: 7061938 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5489. Min Act: -0.1700
Data Index: 5874721 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5489. Min Act: -0.1700
Data Index: 4395084 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5801. Min Act: -0.1700
Data Index: 3483270 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5489. Min Act: -0.1700
Data Index: 144797 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1450264 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.5176. Min Act: -0.1700
Data Index: 3831959 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.4864. Min Act: -0.1700
Data Index: 3429205 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.4864. Min Act: -0.1700
Data Index: 1488325 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7729411 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0176. Min Range: -6.0176
Max Act: 5.4551. Min Act: -0.1700
Data Index: 4233524 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19