Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.3666. Min Act: -0.1700
Data Index: 255572 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.3666. Min Act: -0.1700
Data Index: 7484044 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.3041. Min Act: -0.1700
Data Index: 1000237 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2728. Min Act: -0.1700
Data Index: 2353725 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2416. Min Act: -0.1700
Data Index: 6141543 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.3041. Min Act: -0.1700
Data Index: 732842 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2728. Min Act: -0.1700
Data Index: 8326256 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2103. Min Act: -0.1700
Data Index: 2095295 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2103. Min Act: -0.1700
Data Index: 1067331 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2416. Min Act: -0.1700
Data Index: 8168897 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2103. Min Act: -0.1700
Data Index: 1610527 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2103. Min Act: -0.1700
Data Index: 7625158 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.2103. Min Act: -0.1700
Data Index: 7666476 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1791. Min Act: -0.1700
Data Index: 7033569 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1791. Min Act: -0.1700
Data Index: 6575560 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1791. Min Act: -0.1700
Data Index: 2337188 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1478. Min Act: -0.1700
Data Index: 1824431 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1791. Min Act: -0.1700
Data Index: 8330451 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1791. Min Act: -0.1700
Data Index: 3980442 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3666. Min Range: -5.3666
Max Act: 5.1166. Min Act: -0.1700
Data Index: 4321714 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19