Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.4983. Min Act: -0.1700
Data Index: 6788128 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.3420. Min Act: -0.1700
Data Index: 7100819 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.3108. Min Act: -0.1700
Data Index: 3433734 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.2795. Min Act: -0.1700
Data Index: 3780897 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.2795. Min Act: -0.1700
Data Index: 3162359 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1858. Min Act: -0.1700
Data Index: 8631501 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 7836962 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 3473097 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 3437980 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 2046740 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 1923746 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 1431828 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1545. Min Act: -0.1700
Data Index: 6954105 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1233. Min Act: -0.1700
Data Index: 3433733 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1233. Min Act: -0.1700
Data Index: 5552255 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1233. Min Act: -0.1700
Data Index: 8185191 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1233. Min Act: -0.1700
Data Index: 5853166 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.1233. Min Act: -0.1700
Data Index: 6274069 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.0920. Min Act: -0.1700
Data Index: 4055646 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4983. Min Range: -6.4983
Max Act: 6.0920. Min Act: -0.1700
Data Index: 7598611 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19