Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1151 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.9915. Min Act: -0.1700
Data Index: 2869224 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.9290. Min Act: -0.1700
Data Index: 1433341 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8665. Min Act: -0.1700
Data Index: 12851 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8352. Min Act: -0.1700
Data Index: 35340 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8352. Min Act: -0.1700
Data Index: 6970824 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8352. Min Act: -0.1700
Data Index: 1468030 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8039. Min Act: -0.1700
Data Index: 5900331 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8039. Min Act: -0.1700
Data Index: 6009465 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7726. Min Act: -0.1700
Data Index: 78961 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.8039. Min Act: -0.1700
Data Index: 3013917 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7726. Min Act: -0.1700
Data Index: 8367687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7726. Min Act: -0.1700
Data Index: 5726443 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7414. Min Act: -0.1700
Data Index: 1081849 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7101. Min Act: -0.1700
Data Index: 2813857 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7414. Min Act: -0.1700
Data Index: 1467825 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7414. Min Act: -0.1700
Data Index: 5191265 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7414. Min Act: -0.1700
Data Index: 4764202 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7414. Min Act: -0.1700
Data Index: 4683857 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7726. Min Act: -0.1700
Data Index: 1712714 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9915. Min Range: -3.9915
Max Act: 3.7414. Min Act: -0.1700
Data Index: 282861 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19