Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.4169. Min Act: -0.1700
Data Index: 6299967 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3542. Min Act: -0.1700
Data Index: 7951172 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3385. Min Act: -0.1700
Data Index: 7688470 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3385. Min Act: -0.1700
Data Index: 6862378 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3385. Min Act: -0.1700
Data Index: 1993787 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3385. Min Act: -0.1700
Data Index: 649081 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3228. Min Act: -0.1700
Data Index: 3392285 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3228. Min Act: -0.1700
Data Index: 7688469 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 7098240 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 7133802 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 3244664 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3228. Min Act: -0.1700
Data Index: 7019093 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 7688468 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 4018619 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.2914. Min Act: -0.1700
Data Index: 1898075 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 6221826 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 1233831 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 8785256 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.3071. Min Act: -0.1700
Data Index: 4901666 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4169. Min Range: -3.4169
Max Act: 3.2914. Min Act: -0.1700
Data Index: 2195672 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19