Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.9641. Min Act: -0.1700
Data Index: 7542468 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.9131. Min Act: -0.1700
Data Index: 1488526 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8961. Min Act: -0.1700
Data Index: 3547514 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8790. Min Act: -0.1700
Data Index: 7542469 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8961. Min Act: -0.1700
Data Index: 8249821 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8790. Min Act: -0.1694
Data Index: 8200433 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8619. Min Act: -0.1700
Data Index: 411450 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8534. Min Act: -0.1700
Data Index: 7885520 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8534. Min Act: -0.1700
Data Index: 7965926 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8448. Min Act: -0.1700
Data Index: 8006083 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8448. Min Act: -0.1700
Data Index: 3364944 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8362. Min Act: -0.1700
Data Index: 7086005 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8276. Min Act: -0.1700
Data Index: 8785262 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8276. Min Act: -0.1700
Data Index: 6346202 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8191. Min Act: -0.1700
Data Index: 3854589 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8191. Min Act: -0.1700
Data Index: 6340279 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8191. Min Act: -0.1700
Data Index: 3181518 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8105. Min Act: -0.1700
Data Index: 7906616 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8191. Min Act: -0.1699
Data Index: 6695253 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9641. Min Range: -1.9641
Max Act: 1.8105. Min Act: -0.1700
Data Index: 6720905 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19