Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 733 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0041. Min Range: -2.0041
Max Act: 2.0041. Min Act: -0.1700
Data Index: 8569027 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0041. Min Range: -2.0041
Max Act: 2.0041. Min Act: -0.1700
Data Index: 5991896 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.9193. Min Act: -0.1700
Data Index: 7878289 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.9364. Min Act: -0.1700
Data Index: 3771974 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.9108. Min Act: -0.1700
Data Index: 4900632 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8938. Min Act: -0.1700
Data Index: 1702064 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8767. Min Act: -0.1700
Data Index: 1126687 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8938. Min Act: -0.1700
Data Index: 6167354 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8852. Min Act: -0.1700
Data Index: 3598652 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8681. Min Act: -0.1700
Data Index: 2148522 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8510. Min Act: -0.1700
Data Index: 5548118 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8510. Min Act: -0.1700
Data Index: 5385683 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8425. Min Act: -0.1700
Data Index: 5004319 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8339. Min Act: -0.1700
Data Index: 7777340 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8596. Min Act: -0.1700
Data Index: 5429742 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8425. Min Act: -0.1700
Data Index: 2629476 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8425. Min Act: -0.1700
Data Index: 8231968 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8339. Min Act: -0.1700
Data Index: 6166704 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8253. Min Act: -0.1700
Data Index: 7777341 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0041. Min Range: -2.0041
Max Act: 1.8253. Min Act: -0.1700
Data Index: 2022106 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19