Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.0411. Min Range: -9.0411
Max Act: 9.0411. Min Act: -0.1700
Data Index: 1523012 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.7911. Min Act: -0.1700
Data Index: 4947620 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.6661. Min Act: -0.1700
Data Index: 2934242 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.6036. Min Act: -0.1700
Data Index: 1562822 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.5411. Min Act: -0.1700
Data Index: 6663319 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4474. Min Act: -0.1700
Data Index: 2558251 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.6036. Min Act: -0.1700
Data Index: 1860614 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4786. Min Act: -0.1700
Data Index: 4385395 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4474. Min Act: -0.1700
Data Index: 2004339 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.6661. Min Act: -0.1700
Data Index: 1976225 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4786. Min Act: -0.1700
Data Index: 6592641 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4474. Min Act: -0.1700
Data Index: 470558 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4161. Min Act: -0.1700
Data Index: 3762857 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.3536. Min Act: -0.1700
Data Index: 6387487 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4161. Min Act: -0.1700
Data Index: 430752 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.3536. Min Act: -0.1700
Data Index: 2870939 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4161. Min Act: -0.1700
Data Index: 3873195 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.3536. Min Act: -0.1700
Data Index: 4078081 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.4161. Min Act: -0.1700
Data Index: 3480502 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0411. Min Range: -9.0411
Max Act: 8.2911. Min Act: -0.1700
Data Index: 3809963 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19