Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.9253. Min Act: -0.1700
Data Index: 6837366 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.9566. Min Act: -0.1700
Data Index: 6837359 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6441. Min Act: -0.1700
Data Index: 795909 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.6441. Min Act: -0.1700
Data Index: 4916685 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.5503. Min Act: -0.1700
Data Index: 4645714 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4253. Min Act: -0.1700
Data Index: 4350135 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4253. Min Act: -0.1700
Data Index: 1344185 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4253. Min Act: -0.1700
Data Index: 6837361 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.4253. Min Act: -0.1700
Data Index: 5376827 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.3003. Min Act: -0.1700
Data Index: 5674741 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.2691. Min Act: -0.1700
Data Index: 433480 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.3003. Min Act: -0.1700
Data Index: 5556236 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.3003. Min Act: -0.1700
Data Index: 969924 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.1441. Min Act: -0.1700
Data Index: 7801194 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.2691. Min Act: -0.1700
Data Index: 5062333 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.2378. Min Act: -0.1700
Data Index: 6746625 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.1753. Min Act: -0.1700
Data Index: 2359702 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.1128. Min Act: -0.1700
Data Index: 7269897 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.2066. Min Act: -0.1700
Data Index: 4741014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9566. Min Range: -5.9566
Max Act: 5.1753. Min Act: -0.1700
Data Index: 3792367 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19