Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.1710. Min Act: -0.1700
Data Index: 4185278 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0772. Min Act: -0.1700
Data Index: 3241363 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1710. Min Range: -4.1710
Max Act: 4.0147. Min Act: -0.1700
Data Index: 4659058 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9834. Min Act: -0.1700
Data Index: 4446841 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9834. Min Act: -0.1700
Data Index: 7593898 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9522. Min Act: -0.1700
Data Index: 4656740 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 4610378 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9522. Min Act: -0.1700
Data Index: 5358697 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9522. Min Act: -0.1700
Data Index: 4017232 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 8059273 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6513934 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9053. Min Act: -0.1700
Data Index: 6410076 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6269386 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9053. Min Act: -0.1700
Data Index: 4750079 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 6068908 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9053. Min Act: -0.1700
Data Index: 7838420 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9053. Min Act: -0.1700
Data Index: 1323447 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 2191482 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9209. Min Act: -0.1700
Data Index: 1257216 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1710. Min Range: -4.1710
Max Act: 3.9053. Min Act: -0.1700
Data Index: 533534 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19