Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4920. Min Act: -0.1700
Data Index: 8528963 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4920. Min Act: -0.1700
Data Index: 6987945 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4480. Min Act: -0.1670
Data Index: 836851 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4304. Min Act: -0.1690
Data Index: 3071724 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4304. Min Act: -0.1700
Data Index: 4653744 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4260. Min Act: -0.1700
Data Index: 883835 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4260. Min Act: -0.1698
Data Index: 8546716 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4392. Min Act: -0.1698
Data Index: 8103780 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4216. Min Act: -0.1700
Data Index: 7978286 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4128. Min Act: -0.1638
Data Index: 3454803 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4172. Min Act: -0.1698
Data Index: 8119335 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4084. Min Act: -0.1700
Data Index: 5836524 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4128. Min Act: -0.1697
Data Index: 4131020 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.3996. Min Act: -0.1684
Data Index: 7428190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4084. Min Act: -0.1700
Data Index: 6235497 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4040. Min Act: -0.1697
Data Index: 2082743 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.4128. Min Act: -0.1678
Data Index: 4848917 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.3952. Min Act: -0.1700
Data Index: 6610184 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.3952. Min Act: -0.1700
Data Index: 1139960 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4920. Min Range: -1.4920
Max Act: 1.3952. Min Act: -0.1700
Data Index: 2149950 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19