Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.2163. Min Act: -0.1700
Data Index: 7178206 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1850. Min Act: -0.1700
Data Index: 3961197 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1850. Min Act: -0.1700
Data Index: 5060168 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1538. Min Act: -0.1700
Data Index: 5302138 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1538. Min Act: -0.1700
Data Index: 7265951 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.1538. Min Act: -0.1700
Data Index: 8236490 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0913. Min Act: -0.1700
Data Index: 954706 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0600. Min Act: -0.1700
Data Index: 5126986 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0288. Min Act: -0.1700
Data Index: 3118713 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 6374396 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0288. Min Act: -0.1700
Data Index: 4451970 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2163. Min Range: -5.2163
Max Act: 5.0288. Min Act: -0.1700
Data Index: 3560127 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 176546 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 5707347 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 4116586 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 1915240 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 2578280 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9975. Min Act: -0.1700
Data Index: 2087621 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 5120720 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2163. Min Range: -5.2163
Max Act: 4.9663. Min Act: -0.1700
Data Index: 8671484 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19