Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 304 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0145. Min Range: -8.0145
Max Act: 8.0145. Min Act: -0.1700
Data Index: 1107002 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.7645. Min Act: -0.1700
Data Index: 7142352 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.6707. Min Act: -0.1700
Data Index: 4916614 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.6395. Min Act: -0.1700
Data Index: 1106989 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.6395. Min Act: -0.1700
Data Index: 1106971 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.6395. Min Act: -0.1700
Data Index: 6784937 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.5770. Min Act: -0.1700
Data Index: 1106979 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.5145. Min Act: -0.1700
Data Index: 7142350 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.5145. Min Act: -0.1700
Data Index: 904287 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.4832. Min Act: -0.1700
Data Index: 957433 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.4832. Min Act: -0.1700
Data Index: 1106962 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.4832. Min Act: -0.1700
Data Index: 4465135 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3895. Min Act: -0.1700
Data Index: 6075028 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3895. Min Act: -0.1700
Data Index: 1106995 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3895. Min Act: -0.1700
Data Index: 5512823 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3582. Min Act: -0.1700
Data Index: 1365305 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.2645. Min Act: -0.1700
Data Index: 7142351 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3895. Min Act: -0.1700
Data Index: 4843455 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3582. Min Act: -0.1700
Data Index: 4745070 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0145. Min Range: -8.0145
Max Act: 7.3582. Min Act: -0.1700
Data Index: 5700333 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19