Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1796 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.2573. Min Act: -0.1700
Data Index: 6757352 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.1944. Min Act: -0.1700
Data Index: 7305573 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.1472. Min Act: -0.1700
Data Index: 1623955 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.1314. Min Act: -0.1700
Data Index: 4892030 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.1314. Min Act: -0.1700
Data Index: 1469956 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.1314. Min Act: -0.1700
Data Index: 8429588 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.1157. Min Act: -0.1700
Data Index: 99587 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0999. Min Act: -0.1700
Data Index: 5821407 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0526. Min Act: -0.1700
Data Index: 3784066 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0368. Min Act: -0.1700
Data Index: 8036142 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0368. Min Act: -0.1700
Data Index: 1281831 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0368. Min Act: -0.1700
Data Index: 3810321 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0210. Min Act: -0.1700
Data Index: 2180140 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0368. Min Act: -0.1700
Data Index: 753351 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0052. Min Act: -0.1700
Data Index: 4233419 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2573. Min Range: -3.2573
Max Act: 2.9894. Min Act: -0.1700
Data Index: 3380175 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0052. Min Act: -0.1700
Data Index: 4365605 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2573. Min Range: -3.2573
Max Act: 2.9894. Min Act: -0.1700
Data Index: 2959530 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2573. Min Range: -3.2573
Max Act: 3.0052. Min Act: -0.1700
Data Index: 2900604 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2573. Min Range: -3.2573
Max Act: 2.9736. Min Act: -0.1700
Data Index: 4370438 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19