Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3806 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.6277. Min Act: -0.1700
Data Index: 12432 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.5652. Min Act: -0.1700
Data Index: 7280236 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.3777. Min Act: -0.1700
Data Index: 7354785 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.2527. Min Act: -0.1700
Data Index: 783733 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.0027. Min Act: -0.1700
Data Index: 1389757 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.1277. Min Act: -0.1700
Data Index: 2771766 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.0652. Min Act: -0.1700
Data Index: 538793 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.0027. Min Act: -0.1700
Data Index: 698798 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8777. Min Act: -0.1700
Data Index: 6005326 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6277. Min Range: -9.6277
Max Act: 9.0027. Min Act: -0.1700
Data Index: 3576033 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.9402. Min Act: -0.1700
Data Index: 740199 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8152. Min Act: -0.1700
Data Index: 2218891 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8152. Min Act: -0.1700
Data Index: 7744259 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8152. Min Act: -0.1700
Data Index: 1270538 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8777. Min Act: -0.1700
Data Index: 4833681 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8152. Min Act: -0.1700
Data Index: 2931668 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.7527. Min Act: -0.1700
Data Index: 5852456 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.7527. Min Act: -0.1700
Data Index: 2348154 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.7527. Min Act: -0.1700
Data Index: 2614689 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6277. Min Range: -9.6277
Max Act: 8.8152. Min Act: -0.1700
Data Index: 495103 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19