Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3671 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.8981. Min Act: -0.1700
Data Index: 1967616 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.8981. Min Act: -0.1700
Data Index: 6947178 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.8044. Min Act: -0.1700
Data Index: 2652105 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.7731. Min Act: -0.1700
Data Index: 4161572 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.6794. Min Act: -0.1700
Data Index: 901266 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.5856. Min Act: -0.1700
Data Index: 4899623 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.6169. Min Act: -0.1700
Data Index: 7655621 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.5544. Min Act: -0.1700
Data Index: 7094191 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4919. Min Act: -0.1700
Data Index: 8678841 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4919. Min Act: -0.1700
Data Index: 6769050 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4606. Min Act: -0.1700
Data Index: 5536711 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4294. Min Act: -0.1700
Data Index: 7953244 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4294. Min Act: -0.1700
Data Index: 6945308 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4294. Min Act: -0.1700
Data Index: 4150426 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4294. Min Act: -0.1700
Data Index: 8784386 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.4294. Min Act: -0.1700
Data Index: 5003185 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.3981. Min Act: -0.1700
Data Index: 7840577 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.3981. Min Act: -0.1700
Data Index: 2673027 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.3981. Min Act: -0.1700
Data Index: 7094205 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8981. Min Range: -6.8981
Max Act: 6.3981. Min Act: -0.1700
Data Index: 59520 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19