Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1121 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.9168. Min Act: -0.1699
Data Index: 2753578 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.8231. Min Act: -0.1700
Data Index: 6551944 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.8231. Min Act: -0.1700
Data Index: 8068783 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.6981. Min Act: -0.1700
Data Index: 4589205 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.6356. Min Act: -0.1700
Data Index: 8642761 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.6356. Min Act: -0.1700
Data Index: 1216554 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.6043. Min Act: -0.1700
Data Index: 3797449 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 3512308 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5731. Min Act: -0.1700
Data Index: 5118461 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.6043. Min Act: -0.1700
Data Index: 346460 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.6043. Min Act: -0.1700
Data Index: 4046808 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5731. Min Act: -0.1700
Data Index: 6358087 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5106. Min Act: -0.1700
Data Index: 3004203 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 8419072 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.4481. Min Act: -0.1700
Data Index: 6386193 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5106. Min Act: -0.1700
Data Index: 2642620 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5731. Min Act: -0.1700
Data Index: 7847229 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 3534843 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5418. Min Act: -0.1700
Data Index: 792894 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9168. Min Range: -6.9168
Max Act: 6.5106. Min Act: -0.1700
Data Index: 6923974 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #19