Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.9987. Min Act: -0.1700
Data Index: 2314476 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.8425. Min Act: -0.1700
Data Index: 5580343 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.8112. Min Act: -0.1700
Data Index: 1377072 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7800. Min Act: -0.1700
Data Index: 1146241 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7487. Min Act: -0.1700
Data Index: 6232880 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7487. Min Act: -0.1700
Data Index: 3359008 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7800. Min Act: -0.1700
Data Index: 2967310 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7487. Min Act: -0.1700
Data Index: 2473782 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7175. Min Act: -0.1700
Data Index: 3805229 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7487. Min Act: -0.1700
Data Index: 1889949 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7175. Min Act: -0.1700
Data Index: 5359688 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7175. Min Act: -0.1700
Data Index: 634712 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.7175. Min Act: -0.1700
Data Index: 1277269 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6862. Min Act: -0.1700
Data Index: 8228706 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6986116 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6862. Min Act: -0.1700
Data Index: 4619686 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6862. Min Act: -0.1700
Data Index: 6604033 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6550. Min Act: -0.1700
Data Index: 5410233 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6550. Min Act: -0.1700
Data Index: 1364344 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9987. Min Range: -5.9987
Max Act: 5.6550. Min Act: -0.1700
Data Index: 1981625 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19