Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.3073. Min Act: -0.1700
Data Index: 8325119 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.2578. Min Act: -0.1700
Data Index: 6662209 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.2248. Min Act: -0.1700
Data Index: 6490420 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.2413. Min Act: -0.1700
Data Index: 4113116 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.2248. Min Act: -0.1700
Data Index: 2209987 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1916. Min Act: -0.1700
Data Index: 5876288 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1583. Min Act: -0.1700
Data Index: 8321186 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1583. Min Act: -0.1700
Data Index: 4244586 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1250. Min Act: -0.1700
Data Index: 7257341 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1417. Min Act: -0.1700
Data Index: 8437638 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1250. Min Act: -0.1700
Data Index: 5359855 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1250. Min Act: -0.1700
Data Index: 741136 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1082. Min Act: -0.1700
Data Index: 6314529 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1250. Min Act: -0.1700
Data Index: 7323813 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1082. Min Act: -0.1700
Data Index: 7134545 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.0747. Min Act: -0.1700
Data Index: 5026293 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1082. Min Act: -0.1700
Data Index: 8467322 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.1250. Min Act: -0.1700
Data Index: 4847372 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.0915. Min Act: -0.1700
Data Index: 8026966 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3073. Min Range: -2.3073
Max Act: 2.0915. Min Act: -0.1700
Data Index: 8169427 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19